Peter L. Bartlett

340 papers A* 84A 18B 6C 2Journal 184Unranked 42

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data. CoRR Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
2026	J	`jnl`	Hard labels sampled from sparse targets mislead rotation invariant algorithms. CoRR Avrajit Ghosh, Bin Yu, Manfred K. Warmuth, Peter L. Bartlett
2026	J	`jnl`	Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning. CoRR Gautam Goel, Mahdi Soltanolkotabi, Peter L. Bartlett
2025	J	`jnl`	A result relating convex n-widths to covering numbers with some applications to neural networks. CoRR Jonathan Baxter, Peter L. Bartlett
2025	A*	`conf`	Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression. ICML Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu
2025	J	`jnl`	Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression. CoRR Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu
2025	J	`jnl`	Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification. CoRR Alexander Tsigler, Luiz F. O. Chamon, Spencer Frei, Peter L. Bartlett
2025	J	`jnl`	Contextual Bandits with Stage-wise Constraints. J. Mach. Learn. Res. Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett
2025	A*	`conf`	Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes. ICML Ruiqi Zhang, Jingfeng Wu, Peter L. Bartlett
2025	A*	`conf`	Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks. ICML Yuhang Cai, Kangjie Zhou, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett
2025	J	`jnl`	Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks. CoRR Yuhang Cai, Kangjie Zhou, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett
2025	A	`conf`	Implicit Diffusion: Efficient optimization through stochastic sampling. AISTATS Pierre Marion, Anna Korba, Peter L. Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
2025	J	`jnl`	Improved Scaling Laws in Linear Regression via Data Reuse. CoRR Licong Lin, Jingfeng Wu, Peter L. Bartlett
2025	J	`jnl`	Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression. CoRR Jingfeng Wu, Pierre Marion, Peter L. Bartlett
2025	J	`jnl`	Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes. CoRR Ruiqi Zhang, Jingfeng Wu, Licong Lin, Peter L. Bartlett
2025	J	`jnl`	On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension. J. Mach. Learn. Res. Saptarshi Chakraborty, Peter L. Bartlett
2025	J	`jnl`	Reinforcement Learning in POMDP's via Direct Gradient Ascent. CoRR Jonathan Baxter, Peter L. Bartlett
2025	J	`jnl`	Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization. CoRR Jingfeng Wu, Peter L. Bartlett, Jason D. Lee, Sham M. Kakade, Bin Yu
2025	A	`conf`	Statistical Guarantees for Unpaired Image-to-Image Cross-Domain Analysis using GANs. AISTATS Saptarshi Chakraborty, Peter L. Bartlett
2024	J	`jnl`	A Diffusion Process Perspective on Posterior Contraction Rates for Parameters. SIAM J. Math. Data Sci. Wenlong Mou, Nhat Ho, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2024	J	`jnl`	A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data. CoRR Saptarshi Chakraborty, Peter L. Bartlett
2024	J	`jnl`	A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data. CoRR Saptarshi Chakraborty, Peter L. Bartlett
2024	A*	`conf`	A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data. ICLR Saptarshi Chakraborty, Peter L. Bartlett
2024	J	`jnl`	A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data. CoRR Saptarshi Chakraborty, Peter L. Bartlett
2024	—	`conf`	Can a transformer represent a Kalman filter? L4DC Gautam Goel, Peter L. Bartlett
2024	J	`jnl`	Contextual Bandits with Stage-wise Constraints. CoRR Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett
2024	J	`jnl`	Corrigendum to "Prediction, learning, uniform convergence, and scale-sensitive dimensions" [J. Comput. Syst. Sci. 56 (2) (1998) 174-190]. J. Comput. Syst. Sci. Peter L. Bartlett, Philip M. Long
2024	A*	`conf`	Fast Best-of-N Decoding via Speculative Rejection. NeurIPS Hanshi Sun, Momin Haider, Ruiqi Zhang, Huitao Yang, Jiahao Qiu, Ming Yin, Mengdi Wang, Peter L. Bartlett, Andrea Zanette
2024	J	`jnl`	Fast Best-of-N Decoding via Speculative Rejection. CoRR Hanshi Sun, Momin Haider, Ruiqi Zhang, Huitao Yang, Jiahao Qiu, Ming Yin, Mengdi Wang, Peter L. Bartlett, Andrea Zanette
2024	J	`jnl`	FutureFill: Fast Generation from Convolutional Sequence Models. CoRR Naman Agarwal, Xinyi Chen, Evan Dogariu, Vladimir Feinberg, Daniel Suo, Peter L. Bartlett, Elad Hazan
2024	A*	`conf`	How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? ICLR Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L. Bartlett
2024	J	`jnl`	Implicit Diffusion: Efficient Optimization through Stochastic Sampling. CoRR Pierre Marion, Anna Korba, Peter L. Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
2024	A*	`conf`	In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization. NeurIPS Ruiqi Zhang, Jingfeng Wu, Peter L. Bartlett
2024	J	`jnl`	In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization. CoRR Ruiqi Zhang, Jingfeng Wu, Peter L. Bartlett
2024	A*	`conf`	Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency. COLT Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu
2024	J	`jnl`	Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency. CoRR Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu
2024	A*	`conf`	Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization. NeurIPS Yuhang Cai, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett
2024	J	`jnl`	Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization. CoRR Yuhang Cai, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett
2024	J	`jnl`	On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension. CoRR Saptarshi Chakraborty, Peter L. Bartlett
2024	A*	`conf`	Scaling Laws in Linear Regression: Compute, Parameters, and Data. NeurIPS Licong Lin, Jingfeng Wu, Sham M. Kakade, Peter L. Bartlett, Jason D. Lee
2024	J	`jnl`	Scaling Laws in Linear Regression: Compute, Parameters, and Data. CoRR Licong Lin, Jingfeng Wu, Sham M. Kakade, Peter L. Bartlett, Jason D. Lee
2024	J	`jnl`	Sharpness-Aware Minimization and the Edge of Stability. J. Mach. Learn. Res. Philip M. Long, Peter L. Bartlett
2024	J	`jnl`	Trained Transformers Learn Linear Models In-Context. J. Mach. Learn. Res. Ruiqi Zhang, Spencer Frei, Peter L. Bartlett
2023	J	`jnl`	A Complete Characterization of Linear Estimators for Offline Policy Evaluation. J. Mach. Learn. Res. Juan C. Perdomo, Akshay Krishnamurthy, Peter L. Bartlett, Sham M. Kakade
2023	B	`conf`	An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit. ALT Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
2023	A*	`conf`	Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization. COLT Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro
2023	J	`jnl`	Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization. CoRR Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro
2023	J	`jnl`	Benign overfitting in ridge regression. J. Mach. Learn. Res. Alexander Tsigler, Peter L. Bartlett
2023	J	`jnl`	Can a Transformer Represent a Kalman Filter? CoRR Gautam Goel, Peter L. Bartlett
2023	J	`jnl`	How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? CoRR Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L. Bartlett
2023	A*	`conf`	Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data. ICLR Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro, Wei Hu
2023	J	`jnl`	Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions. CoRR Peter L. Bartlett, Philip M. Long
2023	J	`jnl`	Random Feature Amplification: Feature Learning and Generalization in Neural Networks. J. Mach. Learn. Res. Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
2023	J	`jnl`	Sharpness-Aware Minimization and the Edge of Stability. CoRR Philip M. Long, Peter L. Bartlett
2023	A*	`conf`	The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks. NeurIPS Spencer Frei, Gal Vardi, Peter L. Bartlett, Nati Srebro
2023	J	`jnl`	The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks. CoRR Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro
2023	J	`jnl`	The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima. J. Mach. Learn. Res. Peter L. Bartlett, Philip M. Long, Olivier Bousquet
2023	J	`jnl`	Trained Transformers Learn Linear Models In-Context. CoRR Ruiqi Zhang, Spencer Frei, Peter L. Bartlett
2022	J	`jnl`	A Sharp Characterization of Linear Estimators for Offline Policy Evaluation. CoRR Juan C. Perdomo, Akshay Krishnamurthy, Peter L. Bartlett, Sham M. Kakade
2022	J	`jnl`	An Efficient Sampling Algorithm for Non-smooth Composite Potentials. J. Mach. Learn. Res. Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright, Peter L. Bartlett
2022	A*	`conf`	Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. COLT Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
2022	J	`jnl`	Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. CoRR Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
2022	A*	`conf`	Generalization Bounds for Data-Driven Numerical Linear Algebra. COLT Peter L. Bartlett, Piotr Indyk, Tal Wagner
2022	J	`jnl`	Generalization Bounds for Data-Driven Numerical Linear Algebra. CoRR Peter L. Bartlett, Piotr Indyk, Tal Wagner
2022	J	`jnl`	Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data. CoRR Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro, Wei Hu
2022	J	`jnl`	Joint Representation Training in Sequential Tasks with Shared Structure. CoRR Aldo Pacchiano, Ofir Nachum, Nilesh Tripuraneni, Peter L. Bartlett
2022	J	`jnl`	Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency. CoRR Wenlong Mou, Martin J. Wainwright, Peter L. Bartlett
2022	A*	`conf`	Optimal Mean Estimation without a Variance. COLT Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, Michael I. Jordan
2022	A*	`conf`	Optimal and instance-dependent guarantees for Markovian linear stochastic approximation. COLT Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright, Peter L. Bartlett
2022	J	`jnl`	Optimal variance-reduced stochastic approximation in Banach spaces. CoRR Wenlong Mou, Koulik Khamaru, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2022	J	`jnl`	Random Feature Amplification: Feature Learning and Generalization in Neural Networks. CoRR Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
2022	J	`jnl`	The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima. CoRR Peter L. Bartlett, Philip M. Long, Olivier Bousquet
2022	J	`jnl`	The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	A*	`conf`	Adversarial Examples in Multi-Layer Random ReLU Networks. NeurIPS Peter L. Bartlett, Sébastien Bubeck, Yeshwanth Cherapanamjeri
2021	J	`jnl`	Adversarial Examples in Multi-Layer Random ReLU Networks. CoRR Peter L. Bartlett, Sébastien Bubeck, Yeshwanth Cherapanamjeri
2021	A	`conf`	Agnostic Learning with Unknown Utilities. ITCS Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt
2021	J	`jnl`	Agnostic learning with unknown utilities. CoRR Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt
2021	J	`jnl`	An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit. CoRR Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
2021	J	`jnl`	Deep learning: a statistical viewpoint. Acta Numer. Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin
2021	J	`jnl`	Deep learning: a statistical viewpoint. CoRR Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin
2021	A*	`conf`	Dropout: Explicit Forms and Capacity Control. ICML Raman Arora, Peter L. Bartlett, Poorya Mianjy, Nathan Srebro
2021	J	`jnl`	Failures of Model-dependent Generalization Bounds for Least-norm Interpolation. J. Mach. Learn. Res. Peter L. Bartlett, Philip M. Long
2021	J	`jnl`	High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm. J. Mach. Learn. Res. Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2021	J	`jnl`	Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm. CoRR Lin Chen, Bruno Scherrer, Peter L. Bartlett
2021	A*	`conf`	Near Optimal Policy Optimization via REPS. NeurIPS Aldo Pacchiano, Jonathan N. Lee, Peter L. Bartlett, Ofir Nachum
2021	J	`jnl`	Near Optimal Policy Optimization via REPS. CoRR Aldo Pacchiano, Jonathan N. Lee, Peter L. Bartlett, Ofir Nachum
2021	A*	`conf`	On the Theory of Reinforcement Learning with Once-per-Episode Feedback. NeurIPS Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
2021	J	`jnl`	On the Theory of Reinforcement Learning with Once-per-Episode Feedback. CoRR Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
2021	J	`jnl`	Optimal and instance-dependent guarantees for Markovian linear stochastic approximation. CoRR Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright, Peter L. Bartlett
2021	J	`jnl`	Parallelizing Contextual Linear Bandits. CoRR Jeffrey Chan, Aldo Pacchiano, Nilesh Tripuraneni, Yun S. Song, Peter L. Bartlett, Michael I. Jordan
2021	J	`jnl`	Preference learning along multiple criteria: A game-theoretic perspective. CoRR Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright
2021	A	`conf`	Stochastic Bandits with Linear Constraints. AISTATS Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett, Heinrich Jiang
2021	J	`jnl`	The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. CoRR Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	A*	`conf`	Towards a Dimension-Free Understanding of Adaptive Linear Control. COLT Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter L. Bartlett
2021	J	`jnl`	Towards a Dimension-Free Understanding of Adaptive Linear Control. CoRR Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter L. Bartlett
2021	J	`jnl`	When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? J. Mach. Learn. Res. Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	A*	`conf`	When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2021	J	`jnl`	When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? CoRR Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2020	A*	`conf`	Accelerated Message Passing for Entropy-Regularized MAP Inference. ICML Jonathan N. Lee, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	Accelerated Message Passing for Entropy-Regularized MAP Inference. CoRR Jonathan N. Lee, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. J. Mach. Learn. Res. Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
2020	J	`jnl`	Dropout: Explicit Forms and Capacity Control. CoRR Raman Arora, Peter L. Bartlett, Poorya Mianjy, Nathan Srebro
2020	J	`jnl`	Failures of model-dependent generalization bounds for least-norm interpolation. CoRR Peter L. Bartlett, Philip M. Long
2020	A*	`conf`	Greedy Convex Ensemble. IJCAI Thanh Tan Nguyen, Nan Ye, Peter L. Bartlett
2020	A	`conf`	Langevin Monte Carlo without smoothness. AISTATS Niladri S. Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter L. Bartlett
2020	A	`conf`	OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits. AISTATS Niladri S. Chatterji, Vidya Muthukumar, Peter L. Bartlett
2020	A*	`conf`	On Approximate Thompson Sampling with Langevin Algorithms. ICML Eric Mazumdar, Aldo Pacchiano, Yi-An Ma, Michael I. Jordan, Peter L. Bartlett
2020	A*	`conf`	On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration. COLT Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration. CoRR Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	On Thompson Sampling with Langevin Algorithms. CoRR Eric Mazumdar, Aldo Pacchiano, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	Optimal Mean Estimation without a Variance. CoRR Yeshwanth Cherapanamjeri, Nilesh Tripuraneni, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	Optimal Robust Linear Regression in Nearly Linear Time. CoRR Yeshwanth Cherapanamjeri, Efe Aras, Nilesh Tripuraneni, Michael I. Jordan, Nicolas Flammarion, Peter L. Bartlett
2020	J	`jnl`	Oracle lower bounds for stochastic gradient sampling algorithms. CoRR Niladri S. Chatterji, Peter L. Bartlett, Philip M. Long
2020	A*	`conf`	Preference learning along multiple criteria: A game-theoretic perspective. NeurIPS Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright
2020	J	`jnl`	Regret Bound Balancing and Elimination for Model Selection in Bandits and RL. CoRR Aldo Pacchiano, Christoph Dann, Claudio Gentile, Peter L. Bartlett
2020	A*	`conf`	Self-Distillation Amplifies Regularization in Hilbert Space. NeurIPS Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett
2020	J	`jnl`	Self-Distillation Amplifies Regularization in Hilbert Space. CoRR Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett
2020	J	`jnl`	Stochastic Bandits with Linear Constraints. CoRR Aldo Pacchiano, Mohammad Ghavamzadeh, Peter L. Bartlett, Heinrich Jiang
2020	A*	`conf`	Stochastic Gradient and Langevin Processes. ICML Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael I. Jordan
2020	J	`jnl`	When does gradient descent with logistic loss find interpolating two-layer networks? CoRR Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
2019	B	`conf`	A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption. ALT Peter L. Bartlett, Victor Gabillon, Michal Valko
2019	J	`jnl`	An Efficient Sampling Algorithm for Non-smooth Composite Potentials. CoRR Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright, Peter L. Bartlett
2019	J	`jnl`	Bayesian Robustness: A Nonasymptotic Viewpoint. CoRR Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, Michael I. Jordan
2019	J	`jnl`	Benign Overfitting in Linear Regression. CoRR Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler
2019	A	`conf`	Best of many worlds: Robust model selection for online supervised learning. AISTATS Vidya Muthukumar, Mitas Ray, Anant Sahai, Peter L. Bartlett
2019	A*	`conf`	Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning. ICML Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett
2019	A	`conf`	Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. AISTATS Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
2019	A*	`conf`	Fast Mean Estimation with Sub-Gaussian Rates. COLT Yeshwanth Cherapanamjeri, Nicolas Flammarion, Peter L. Bartlett
2019	J	`jnl`	Fast Mean Estimation with Sub-Gaussian Rates. CoRR Yeshwanth Cherapanamjeri, Nicolas Flammarion, Peter L. Bartlett
2019	J	`jnl`	Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks. Neural Comput. Peter L. Bartlett, David P. Helmbold, Philip M. Long
2019	J	`jnl`	Hebbian Synaptic Modifications in Spiking Neurons that Learn. CoRR Peter L. Bartlett, Jonathan Baxter
2019	J	`jnl`	High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm. CoRR Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2019	J	`jnl`	Is There an Analog of Nesterov Acceleration for MCMC? CoRR Yi-An Ma, Niladri S. Chatterji, Xiang Cheng, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan
2019	J	`jnl`	Langevin Monte Carlo without Smoothness. CoRR Niladri S. Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter L. Bartlett
2019	J	`jnl`	Large-Scale Markov Decision Problems via the Linear Programming Dual. CoRR Yasin Abbasi-Yadkori, Peter L. Bartlett, Xi Chen, Alan Malek
2019	J	`jnl`	Learning Near-optimal Convex Combinations of Basis Models with Generalization Guarantees. CoRR Tan M. Nguyen, Nan Ye, Peter L. Bartlett
2019	J	`jnl`	Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks. J. Mach. Learn. Res. Peter L. Bartlett, Nick Harvey, Christopher Liaw, Abbas Mehrabian
2019	J	`jnl`	OSOM: A Simultaneously Optimal Algorithm for Multi-Armed and Linear Contextual Bandits. CoRR Niladri S. Chatterji, Vidya Muthukumar, Peter L. Bartlett
2019	A*	`conf`	Online learning with kernel losses. ICML Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett
2019	A*	`conf`	POLITEX: Regret Bounds for Policy Iteration using Expert Prediction. ICML Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
2019	J	`jnl`	Quantitative Central Limit Theorems for Discrete Stochastic Processes. CoRR Xiang Cheng, Peter L. Bartlett, Michael I. Jordan
2019	J	`jnl`	Quantitative W CoRR Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael I. Jordan
2019	A*	`conf`	Rademacher Complexity for Adversarially Robust Generalization. ICML Dong Yin, Kannan Ramchandran, Peter L. Bartlett
2019	J	`jnl`	Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing. CoRR Wenlong Mou, Nhat Ho, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2019	A*	`conf`	Scale-free adaptive planning for deterministic dynamics & discounted rewards. ICML Peter L. Bartlett, Victor Gabillon, Jennifer Healey, Michal Valko
2019	J	`jnl`	Testing Markov Chains without Hitting. CoRR Yeshwanth Cherapanamjeri, Peter L. Bartlett
2019	A*	`conf`	Testing Symmetric Markov Chains Without Hitting. COLT Yeshwanth Cherapanamjeri, Peter L. Bartlett
2018	J	`jnl`	A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption. CoRR Peter L. Bartlett, Victor Gabillon, Michal Valko
2018	A*	`conf`	Best of both worlds: Stochastic & adversarial best-arm identification. COLT Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, Michal Valko
2018	J	`jnl`	Best of many worlds: Robust model selection for online supervised learning. CoRR Vidya Muthukumar, Mitas Ray, Anant Sahai, Peter L. Bartlett
2018	A*	`conf`	Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. ICML Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett
2018	J	`jnl`	Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. CoRR Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett
2018	B	`conf`	Convergence of Langevin MCMC in KL-divergence. ALT Xiang Cheng, Peter L. Bartlett
2018	J	`jnl`	Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning. CoRR Dong Yin, Yudong Chen, Kannan Ramchandran, Peter L. Bartlett
2018	J	`jnl`	Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. CoRR Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
2018	A	`conf`	FLAG n' FLARE: Fast Linearly-Coupled Adaptive Gradient Methods. AISTATS Xiang Cheng, Fred (Farbod) Roosta, Stefan Palombo, Peter L. Bartlett, Michael W. Mahoney
2018	J	`jnl`	Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation. CoRR Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan
2018	A*	`conf`	Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation. NeurIPS Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan
2018	A	`conf`	Gradient Diversity: a Key Ingredient for Scalable Distributed Learning. AISTATS Dong Yin, Ashwin Pananjady, Maximilian Lam, Dimitris S. Papailiopoulos, Kannan Ramchandran, Peter L. Bartlett
2018	J	`jnl`	Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. CoRR Peter L. Bartlett, David P. Helmbold, Philip M. Long
2018	A*	`conf`	Gradient descent with identity initialization efficiently learns positive definite linear transformations. ICML Peter L. Bartlett, David P. Helmbold, Philip M. Long
2018	A*	`conf`	Horizon-Independent Minimax Linear Regression. NeurIPS Alan Malek, Peter L. Bartlett
2018	A*	`conf`	On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo. ICML Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan
2018	J	`jnl`	On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo. CoRR Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan
2018	J	`jnl`	Online learning with kernel losses. CoRR Aldo Pacchiano, Niladri S. Chatterji, Peter L. Bartlett
2018	J	`jnl`	Rademacher Complexity for Adversarially Robust Generalization. CoRR Dong Yin, Kannan Ramchandran, Peter L. Bartlett
2018	J	`jnl`	Representing smooth functions as compositions of near-identity functions with implications for deep network optimization. CoRR Peter L. Bartlett, Steven N. Evans, Philip M. Long
2018	J	`jnl`	Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting. CoRR Xiang Cheng, Niladri S. Chatterji, Yasin Abbasi-Yadkori, Peter L. Bartlett, Michael I. Jordan
2018	C	`conf`	Two Approximate Dynamic Programming Algorithms for Managing Complete SIS Networks. COMPASS Martin Péron, Peter L. Bartlett, Kai Helge Becker, Kate J. Helmstedt, Iadine Chadès
2018	A*	`conf`	Underdamped Langevin MCMC: A non-asymptotic analysis. COLT Xiang Cheng, Niladri S. Chatterji, Peter L. Bartlett, Michael I. Jordan
2017	—	`conf`	Acceleration and Averaging in Stochastic Descent Dynamics. NIPS Walid Krichene, Peter L. Bartlett
2017	—	`conf`	Alternating minimization for dictionary learning with random initialization. NIPS Niladri S. Chatterji, Peter L. Bartlett
2017	J	`jnl`	Alternating minimization for dictionary learning with random initialization. CoRR Niladri S. Chatterji, Peter L. Bartlett
2017	J	`jnl`	Approximate and Stochastic Greedy Optimization. CoRR Nan Ye, Peter L. Bartlett
2017	J	`jnl`	Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction. IEEE Trans. Inf. Theory Fares Hedayati, Peter L. Bartlett
2017	A*	`conf`	Fast-Tracking Stationary MOMDPs for Adaptive Management Problems. AAAI Martin Péron, Kai Helge Becker, Peter L. Bartlett, Iadine Chades
2017	J	`jnl`	Gradient Diversity Empowers Distributed Learning. CoRR Dong Yin, Ashwin Pananjady, Maximilian Lam, Dimitris S. Papailiopoulos, Kannan Ramchandran, Peter L. Bartlett
2017	A	`conf`	Hit-and-Run for Sampling and Planning in Non-Convex Spaces. AISTATS Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek
2017	—	`conf`	Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem. NIPS Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon
2017	A*	`conf`	Recovery Guarantees for One-hidden-layer Neural Networks. ICML Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon
2017	J	`jnl`	Recovery Guarantees for One-hidden-layer Neural Networks. CoRR Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon
2017	—	`conf`	Spectrally-normalized margin bounds for neural networks. NIPS Peter L. Bartlett, Dylan J. Foster, Matus Telgarsky
2017	J	`jnl`	Spectrally-normalized margin bounds for neural networks. CoRR Peter L. Bartlett, Dylan J. Foster, Matus Telgarsky
2017	J	`jnl`	Underdamped Langevin MCMC: A non-asymptotic analysis. CoRR Xiang Cheng, Niladri S. Chatterji, Peter L. Bartlett, Michael I. Jordan
2016	A	`conf`	A Fast and Reliable Policy Improvement Algorithm. AISTATS Yasin Abbasi-Yadkori, Peter L. Bartlett, Stephen J. Wright
2016	—	`conf`	Adaptive Averaging in Accelerated Descent Dynamics. NIPS Walid Krichene, Alexandre M. Bayen, Peter L. Bartlett
2016	J	`jnl`	FLAG: Fast Linearly-Coupled Adaptive Gradient Method. CoRR Xiang Cheng, Farbod Roosta-Khorasani, Peter L. Bartlett, Michael W. Mahoney
2016	J	`jnl`	Hit-and-Run for Sampling and Planning in Non-Convex Spaces. CoRR Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek
2016	A	`conf`	Improved Learning Complexity in Combinatorial Pure Exploration Bandits. AISTATS Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh, Ronald Ortner, Peter L. Bartlett
2016	J	`jnl`	RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning. CoRR Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel
2015	—	`conf`	Accelerated Mirror Descent in Continuous and Discrete Time. NIPS Walid Krichene, Alexandre M. Bayen, Peter L. Bartlett
2015	A*	`conf`	Large-Scale Markov Decision Problems with KL Control Cost and its Application to Crowdsourcing. ICML Yasin Abbasi-Yadkori, Peter L. Bartlett, Xi Chen, Alan Malek
2015	A*	`conf`	Minimax Fixed-Design Linear Regression. COLT Peter L. Bartlett, Wouter M. Koolen, Alan Malek, Eiji Takimoto, Manfred K. Warmuth
2015	—	`conf`	Minimax Time Series Prediction. NIPS Wouter M. Koolen, Alan Malek, Peter L. Bartlett, Yasin Abbasi-Yadkori
2014	J	`jnl`	Bounding Embeddings of VC Classes into Maximum Classes. CoRR J. Hyam Rubinstein, Benjamin I. P. Rubinstein, Peter L. Bartlett
2014	—	`conf`	Efficient Minimax Strategies for Square Loss Games. NIPS Wouter M. Koolen, Alan Malek, Peter L. Bartlett
2014	—	`conf`	Large-Margin Convex Polytope Machine. NIPS Alex Kantchelian, Michael Carl Tschantz, Ling Huang, Peter L. Bartlett, Anthony D. Joseph, J. Doug Tygar
2014	A*	`conf`	Linear Programming for Large-Scale Markov Decision Problems. ICML Alan Malek, Yasin Abbasi-Yadkori, Peter L. Bartlett
2014	J	`jnl`	Linear Programming for Large-Scale Markov Decision Problems. CoRR Yasin Abbasi-Yadkori, Peter L. Bartlett, Alan Malek
2014	A*	`conf`	Prediction with Limited Advice and Multiarmed Bandits with Paid Observations. ICML Yevgeny Seldin, Peter L. Bartlett, Koby Crammer, Yasin Abbasi-Yadkori
2014	A*	`conf`	Tracking Adversarial Targets. ICML Yasin Abbasi-Yadkori, Peter L. Bartlett, Varun Kanade
2013	J	`jnl`	Advice-Efficient Prediction with Expert Advice CoRR Yevgeny Seldin, Peter L. Bartlett, Koby Crammer
2013	J	`jnl`	Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families CoRR Peter L. Bartlett, Peter Grunwald, Peter Harremoës, Fares Hedayati, Wojciech Kotlowski
2013	A*	`conf`	Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families. COLT Peter L. Bartlett, Peter Grünwald, Peter Harremoës, Fares Hedayati, Wojciech Kotlowski
2013	—	`conf`	How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal. NIPS Jacob D. Abernethy, Peter L. Bartlett, Rafael M. Frongillo, Andre Wibisono
2013	J	`jnl`	Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions CoRR Yasin Abbasi-Yadkori, Peter L. Bartlett, Csaba Szepesvári
2013	—	`conf`	Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions. NIPS Yasin Abbasi-Yadkori, Peter L. Bartlett, Varun Kanade, Yevgeny Seldin, Csaba Szepesvári
2013	A*	`conf`	Open Problem: Adversarial Multiarmed Bandits with Limited Advice. COLT Yevgeny Seldin, Koby Crammer, Peter L. Bartlett
2012	J	`jnl`	A Learning-Based Approach to Reactive Security. IEEE Trans. Dependable Secur. Comput. Adam Barth, Benjamin I. P. Rubinstein, Mukund Sundararajan, John C. Mitchell, Dawn Song, Peter L. Bartlett
2012	—	`ed.`	Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States. NIPS Peter L. Bartlett, Fernando C. N. Pereira, Christopher J. C. Burges, Léon Bottou, Kilian Q. Weinberger
2012	A	`conf`	Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction with Jeffreys Prior. AISTATS Fares Hedayati, Peter L. Bartlett
2012	J	`jnl`	Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization. IEEE Trans. Inf. Theory Alekh Agarwal, Peter L. Bartlett, Pradeep Ravikumar, Martin J. Wainwright
2012	J	`jnl`	Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning. J. Priv. Confidentiality Benjamin I. P. Rubinstein, Peter L. Bartlett, Ling Huang, Nina Taft
2012	J	`jnl`	Oracle inequalities for computationally adaptive model selection CoRR Alekh Agarwal, Peter L. Bartlett, John C. Duchi
2012	J	`jnl`	REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs CoRR Peter L. Bartlett, Ambuj Tewari
2012	J	`jnl`	Randomized Smoothing for Stochastic Optimization. SIAM J. Optim. John C. Duchi, Peter L. Bartlett, Martin J. Wainwright
2012	—	`conf`	Randomized smoothing for (parallel) stochastic optimization. CDC John C. Duchi, Peter L. Bartlett, Martin J. Wainwright
2012	A*	`conf`	The Optimality of Jeffreys Prior for Online Density Estimation and the Asymptotic Normality of Maximum Likelihood Estimators. COLT Fares Hedayati, Peter L. Bartlett
2011	—	`ed.`	Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, Granada, Spain. NIPS John Shawe-Taylor, Richard S. Zemel, Peter L. Bartlett, Fernando C. N. Pereira, Kilian Q. Weinberger
2011	A*	`conf`	Blackwell Approachability and No-Regret Learning are Equivalent. COLT Jacob D. Abernethy, Peter L. Bartlett, Elad Hazan
2011	J	`jnl`	Experiments with Infinite-Horizon, Policy-Gradient Estimation CoRR Peter L. Bartlett, Jonathan Baxter, Lex Weaver
2011	J	`jnl`	Infinite-Horizon Policy-Gradient Estimation CoRR Peter L. Bartlett, Jonathan Baxter
2011	A	`conf`	Learning with Missing Features. UAI Afshin Rostamizadeh, Alekh Agarwal, Peter L. Bartlett
2011	J	`jnl`	Online and Batch Learning Algorithms for Data with Missing Features CoRR Afshin Rostamizadeh, Alekh Agarwal, Peter L. Bartlett
2011	A*	`conf`	Oracle inequalities for computationally budgeted model selection. COLT Alekh Agarwal, John C. Duchi, Peter L. Bartlett, Clément Levrard
2010	—	`conf`	A Learning-Based Approach to Reactive Security. Financial Cryptography Adam Barth, Benjamin I. P. Rubinstein, Mukund Sundararajan, John C. Mitchell, Dawn Song, Peter L. Bartlett
2010	B	`conf`	A Regularization Approach to Metrical Task Systems. ALT Jacob D. Abernethy, Peter L. Bartlett, Niv Buchbinder, Isabelle Stanton
2010	J	`jnl`	A Unifying View of Multiple Kernel Learning CoRR Marius Kloft, Ulrich Rückert, Peter L. Bartlett
2010	—	`conf`	A Unifying View of Multiple Kernel Learning. ECML/PKDD (2) Marius Kloft, Ulrich Rückert, Peter L. Bartlett
2010	J	`jnl`	Blackwell Approachability and Low-Regret Learning are Equivalent CoRR Jacob D. Abernethy, Peter L. Bartlett, Elad Hazan
2010	J	`jnl`	Corrigendum to "Shifting: One-inclusion mistake bounds and sample compression" [J. Comput. System Sci 75 (1) (2009) 37-59]. J. Comput. Syst. Sci. Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein
2010	A*	`conf`	Implicit Online Learning. ICML Brian Kulis, Peter L. Bartlett
2010	J	`jnl`	Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization. CoRR Alekh Agarwal, Peter L. Bartlett, Pradeep Ravikumar, Martin J. Wainwright
2010	J	`jnl`	Learning to act in uncertain environments: technical perspective. Commun. ACM Peter L. Bartlett
2010	A	`conf`	Optimal Allocation Strategies for the Dark Pool Problem. AISTATS Alekh Agarwal, Peter L. Bartlett, Max Dama
2010	B	`conf`	Optimal Online Prediction in Adversarial Environments. ALT Peter L. Bartlett
2010	B	`conf`	Optimal Online Prediction in Adversarial Environments. Discovery Science Peter L. Bartlett
2009	J	`jnl`	A Learning-Based Approach to Reactive Security CoRR Adam Barth, Benjamin I. P. Rubinstein, Mukund Sundararajan, John C. Mitchell, Dawn Xiaodong Song, Peter L. Bartlett
2009	J	`jnl`	A Stochastic View of Optimal Regret through Minimax Duality CoRR Jacob D. Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin
2009	A*	`conf`	A Stochastic View of Optimal Regret through Minimax Duality. COLT Jacob D. Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin
2009	—	`conf`	Information-theoretic lower bounds on the oracle complexity of convex optimization. NIPS Alekh Agarwal, Peter L. Bartlett, Pradeep Ravikumar, Martin J. Wainwright
2009	J	`jnl`	Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning CoRR Benjamin I. P. Rubinstein, Peter L. Bartlett, Ling Huang, Nina Taft
2009	J	`jnl`	Multiview point cloud kernels for semisupervised learning [Lecture Notes]. IEEE Signal Process. Mag. David S. Rosenberg, Vikas Sindhwani, Peter L. Bartlett, Partha Niyogi
2009	A	`conf`	REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs. UAI Peter L. Bartlett, Ambuj Tewari
2009	J	`jnl`	Shifting: One-inclusion mistake bounds and sample compression. J. Comput. Syst. Sci. Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein
2008	J	`jnl`	Classification with a Reject Option using a Hinge Loss. J. Mach. Learn. Res. Peter L. Bartlett, Marten H. Wegkamp
2008	J	`jnl`	Correction to "The Importance of Convexity in Learning With Squared Loss". IEEE Trans. Inf. Theory Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
2008	J	`jnl`	Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks. J. Mach. Learn. Res. Michael Collins, Amir Globerson, Terry Koo, Xavier Carreras, Peter L. Bartlett
2008	A*	`conf`	High-Probability Regret Bounds for Bandit Online Linear Optimization. COLT Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, Sham M. Kakade, Alexander Rakhlin, Ambuj Tewari
2008	—	`conf`	Open problems in the security of learning. AISec Marco Barreno, Peter L. Bartlett, Fuching Jack Chi, Anthony D. Joseph, Blaine Nelson, Benjamin I. P. Rubinstein, Udam Saini, J. Doug Tygar
2008	A*	`conf`	Optimal Stragies and Minimax Lower Bounds for Online Convex Games. COLT Jacob D. Abernethy, Peter L. Bartlett, Alexander Rakhlin, Ambuj Tewari
2007	J	`jnl`	AdaBoost is Consistent. J. Mach. Learn. Res. Peter L. Bartlett, Mikhail Traskin
2007	—	`conf`	Adaptive Online Gradient Descent. NIPS Peter L. Bartlett, Elad Hazan, Alexander Rakhlin
2007	A*	`conf`	Bounded Parameter Markov Decision Processes with Average Reward Criterion. COLT Ambuj Tewari, Peter L. Bartlett
2007	A*	`conf`	Multitask Learning with Expert Advice. COLT Jacob D. Abernethy, Peter L. Bartlett, Alexander Rakhlin
2007	J	`jnl`	On the Consistency of Multiclass Classification Methods. J. Mach. Learn. Res. Ambuj Tewari, Peter L. Bartlett
2007	A*	`conf`	Online discovery of similarity mappings. ICML Alexander Rakhlin, Jacob D. Abernethy, Peter L. Bartlett
2007	—	`conf`	Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs. NIPS Ambuj Tewari, Peter L. Bartlett
2007	J	`jnl`	Sparseness vs Estimating Conditional Probabilities: Some Asymptotic Results. J. Mach. Learn. Res. Peter L. Bartlett, Ambuj Tewari
2007	A	`conf`	The Rademacher Complexity of Co-Regularized Kernel Classes. AISTATS David S. Rosenberg, Peter L. Bartlett
2006	—	`conf`	AdaBoost is Consistent. NIPS Peter L. Bartlett, Mikhail Traskin
2006	—	`conf`	Sample Complexity of Policy Search with Known Dynamics. NIPS Peter L. Bartlett, Ambuj Tewari
2006	—	`conf`	Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds. NIPS Benjamin I. P. Rubinstein, Peter L. Bartlett, J. Hyam Rubinstein
2005	A*	`conf`	On the Consistency of Multiclass Classification Methods. COLT Ambuj Tewari, Peter L. Bartlett
2004	—	`conf`	Exponentiated Gradient Algorithms for Large-margin Structured Classification. NIPS Peter L. Bartlett, Michael Collins, Benjamin Taskar, David A. McAllester
2004	J	`jnl`	Learning the Kernel Matrix with Semidefinite Programming. J. Mach. Learn. Res. Gert R. G. Lanckriet, Nello Cristianini, Peter L. Bartlett, Laurent El Ghaoui, Michael I. Jordan
2004	A*	`conf`	Local Complexities for Empirical Risk Minimization. COLT Peter L. Bartlett, Shahar Mendelson, Petra Philips
2004	A*	`conf`	Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results. COLT Peter L. Bartlett, Ambuj Tewari
2004	J	`jnl`	Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. J. Mach. Learn. Res. Evan Greensmith, Peter L. Bartlett, Jonathan Baxter
2003	—	`conf`	Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates. NIPS Peter L. Bartlett, Michael I. Jordan, Jon D. McAuliffe
2002	—	`conf`	An Introduction to Reinforcement Learning Theory: Value Function Methods. Machine Learning Summer School Peter L. Bartlett
2002	J	`jnl`	Covering numbers for support vector machines. IEEE Trans. Inf. Theory Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson
2002	J	`jnl`	Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning. J. Comput. Syst. Sci. Peter L. Bartlett, Jonathan Baxter
2002	J	`jnl`	Exploiting Random Walks for Learning. Inf. Comput. Peter L. Bartlett, Paul Fischer, Klaus-Uwe Höffgen
2002	J	`jnl`	Generalization Error of Combined Classifiers. J. Comput. Syst. Sci. Llew Mason, Peter L. Bartlett, Mostefa Golea
2002	J	`jnl`	Hardness results for neural network approximation problems. Theor. Comput. Sci. Peter L. Bartlett, Shai Ben-David
2002	A*	`conf`	Learning the Kernel Matrix with Semi-Definite Programming. ICML Gert R. G. Lanckriet, Nello Cristianini, Peter L. Bartlett, Laurent El Ghaoui, Michael I. Jordan
2002	A*	`conf`	Localized Rademacher Complexities. COLT Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson
2002	J	`jnl`	Model Selection and Error Estimation. Mach. Learn. Peter L. Bartlett, Stéphane Boucheron, Gábor Lugosi
2002	—	`book`	Neural Network Learning - Theoretical Foundations. Martin Anthony, Peter L. Bartlett
2002	J	`jnl`	Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. J. Mach. Learn. Res. Peter L. Bartlett, Shahar Mendelson
2001	J	`jnl`	Experiments with Infinite-Horizon, Policy-Gradient Estimation. J. Artif. Intell. Res. Jonathan Baxter, Peter L. Bartlett, Lex Weaver
2001	J	`jnl`	Infinite-Horizon Policy-Gradient Estimation. J. Artif. Intell. Res. Jonathan Baxter, Peter L. Bartlett
2001	—	`conf`	Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. COLT/EuroCOLT Peter L. Bartlett, Shahar Mendelson
2001	—	`conf`	Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. NIPS Evan Greensmith, Peter L. Bartlett, Jonathan Baxter
2000	C	`conf`	Direct gradient-based reinforcement learning. ISCAS Jonathan Baxter, Peter L. Bartlett
2000	J	`jnl`	Direct iterative tuning via spectral analysis. Autom. Leonardo C. Kammer, Robert R. Bitmead, Peter L. Bartlett
2000	A*	`conf`	Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning. COLT Peter L. Bartlett, Jonathan Baxter
2000	J	`jnl`	Function Learning From Interpolation. Comb. Probab. Comput. Martin Anthony, Peter L. Bartlett
2000	J	`jnl`	Improved Generalization Through Explicit Optimization of Margins. Mach. Learn. Llew Mason, Peter L. Bartlett, Jonathan Baxter
2000	J	`jnl`	Learning Changing Concepts by Exploiting the Structure of Change. Mach. Learn. Peter L. Bartlett, Shai Ben-David, Sanjeev R. Kulkarni
2000	A*	`conf`	Model Selection and Error Estimation. COLT Peter L. Bartlett, Stéphane Boucheron, Gábor Lugosi
2000	J	`jnl`	New Support Vector Algorithms. Neural Comput. Bernhard Schölkopf, Alexander J. Smola, Robert C. Williamson, Peter L. Bartlett
2000	J	`jnl`	Profiling in the ASP codesign environment. J. Syst. Archit. Sri Parameswaran, Matthew F. Parkinson, Peter L. Bartlett
2000	A*	`conf`	Reinforcement Learning in POMDP's via Direct Gradient Ascent. ICML Jonathan Baxter, Peter L. Bartlett
2000	—	`conf`	Sparse Greedy Gaussian Process Regression. NIPS Alexander J. Smola, Peter L. Bartlett
2000	—	`conf`	Stochastic optimization of controlled partially observable Markov decision processes. CDC Peter L. Bartlett, Jonathan Baxter
1999	—	`conf`	Boosting Algorithms as Gradient Descent. NIPS Llew Mason, Jonathan Baxter, Peter L. Bartlett, Marcus R. Frean
1999	A*	`conf`	Covering Numbers for Support Vector Machines. COLT Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson
1999	—	`conf`	Hardness Results for Neural Network Approximation Problems. EuroCOLT Peter L. Bartlett, Shai Ben-David
1998	—	`conf`	Almost Linear VC Dimension Bounds for Piecewise Polynomial Networks. NIPS Peter L. Bartlett, Vitaly Maiorov, Ron Meir
1998	J	`jnl`	Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks. Neural Comput. Peter L. Bartlett, Vitaly Maiorov, Ron Meir
1998	—	`conf`	Direct Optimization of Margins Improves Generalization in Combined Classifiers. NIPS Llew Mason, Peter L. Bartlett, Jonathan Baxter
1998	J	`jnl`	Optimal controller properties from closed-loop experiments. Autom. Leonardo C. Kammer, Robert R. Bitmead, Peter L. Bartlett
1998	J	`jnl`	Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions. J. Comput. Syst. Sci. Peter L. Bartlett, Philip M. Long
1998	A*	`ed.`	Proceedings of the Eleventh Annual Conference on Computational Learning Theory, COLT 1998, Madison, Wisconsin, USA, July 24-26, 1998. COLT Peter L. Bartlett, Yishay Mansour
1998	—	`conf`	Shrinking the Tube: A New Support Vector Regression Algorithm. NIPS Bernhard Schölkopf, Peter L. Bartlett, Alexander J. Smola, Robert C. Williamson
1998	J	`jnl`	Structural Risk Minimization Over Data-Dependent Hierarchies. IEEE Trans. Inf. Theory John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony
1998	J	`jnl`	The Importance of Convexity in Learning with Squared Loss. IEEE Trans. Inf. Theory Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1998	J	`jnl`	The Minimax Distortion Redundancy in Empirical Quantizer Design. IEEE Trans. Inf. Theory Peter L. Bartlett, Tamás Linder, Gábor Lugosi
1998	J	`jnl`	The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network. IEEE Trans. Inf. Theory Peter L. Bartlett
1997	—	`conf`	A Minimax Lower Bound for Empirical Quantizer Design. EuroCOLT Peter L. Bartlett, Tamás Linder, Gábor Lugosi
1997	—	`conf`	A Result Relating Convex EuroCOLT Jonathan Baxter, Peter L. Bartlett
1997	J	`jnl`	Correction to 'Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes'. Neural Comput. Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1997	J	`jnl`	Covering numbers for real-valued function classes. IEEE Trans. Inf. Theory Peter L. Bartlett, Sanjeev R. Kulkarni, S. E. Posner
1997	—	`conf`	Generalization in Decision Trees and DNF: Does Size Matter? NIPS Mostefa Golea, Peter L. Bartlett, Wee Sun Lee, Llew Mason
1997	—	`conf`	The Canonical Distortion Measure in Feature Space and 1-NN Classification. NIPS Jonathan Baxter, Peter L. Bartlett
1996	A*	`conf`	A Framework for Structural Risk Minimisation. COLT John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony
1996	J	`jnl`	Efficient agnostic learning of neural networks with bounded fan-in. IEEE Trans. Inf. Theory Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1996	J	`jnl`	Fat-Shattering and the Learnability of Real-Valued Functions. J. Comput. Syst. Sci. Peter L. Bartlett, Philip M. Long, Robert C. Williamson
1996	—	`conf`	For Valid Generalization the Size of the Weights is More Important than the Size of the Network. NIPS Peter L. Bartlett
1996	A*	`conf`	Learning Changing Concepts by Exploiting the Structure of Change. COLT Peter L. Bartlett, Shai Ben-David, Sanjeev R. Kulkarni
1996	A*	`conf`	The Importance of Convexity in Learning with Squared Loss. COLT Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1996	J	`jnl`	The VC Dimension and Pseudodimension of Two-Layer Neural Networks with Discrete Inputs. Neural Comput. Peter L. Bartlett, Robert C. Williamson
1996	J	`jnl`	Valid Generalisation from Approximate Interpolation. Comb. Probab. Comput. Martin Anthony, Peter L. Bartlett, Yuval Ishai, John Shawe-Taylor
1995	—	`conf`	Examples of learning curves from a modified VC-formalism. NIPS Adam Kowalczyk, Jacek Szymanski, Peter L. Bartlett, Robert C. Williamson
1995	—	`conf`	Function learning from interpolation. EuroCOLT Martin Anthony, Peter L. Bartlett
1995	J	`jnl`	Lower Bounds on the VC Dimension of Smoothly Parameterized Function Classes. Neural Comput. Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1995	A*	`conf`	More Theorems about Scale-sensitive Dimensions and Learning. COLT Peter L. Bartlett, Philip M. Long
1995	A*	`conf`	On Efficient Agnostic Learning of Linear Combinations of Basis Functions. COLT Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1994	A*	`conf`	Exploiting Random Walks for Learning. COLT Peter L. Bartlett, Paul Fischer, Klaus-Uwe Höffgen
1994	A*	`conf`	Fat-Shattering and the Learnability of Real-Valued Functions. COLT Peter L. Bartlett, Philip M. Long, Robert C. Williamson
1994	A*	`conf`	Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes. COLT Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1993	A*	`conf`	Lower Bounds on the Vapnik-Chervonenkis Dimension of Multi-Layer Threshold Networks. COLT Peter L. Bartlett
1993	J	`jnl`	Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks. Neural Comput. Peter L. Bartlett
1992	—	`—`	Computational learning theory and neural network learning Peter L. Bartlett
1992	A*	`conf`	Learning With a Slowly Changing Distribution. COLT Peter L. Bartlett
1992	J	`jnl`	Using random weights to train multilayer networks of hard-limiting units. IEEE Trans. Neural Networks Peter L. Bartlett, Tom Downs
1991	A*	`conf`	Investigating the Distribution Assumptions in the Pac Learning Model. COLT Peter L. Bartlett, Robert C. Williamson
1991	—	`conf`	Splines, Rational Functions and Neural Networks. NIPS Robert C. Williamson, Peter L. Bartlett