Matus Telgarsky

82 papers A* 25A 2B 2Journal 44Unranked 8

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis. CoRR Seunghoon Paik, Kangjie Zhou, Matus Telgarsky, Ryan J. Tibshirani
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
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	J	`jnl`	One-layer transformers fail to solve the induction heads task. CoRR Clayton Sanford, Daniel Hsu, Matus Telgarsky
2024	A	`conf`	Spectrum Extraction and Clipping for Implicitly Linear Layers. AISTATS Ali Ebrahimpour Boroojeny, Matus Telgarsky, Hari Sundaram
2024	J	`jnl`	Spectrum Extraction and Clipping for Implicitly Linear Layers. CoRR Ali Ebrahimpour Boroojeny, Matus Telgarsky, Hari Sundaram
2024	A*	`conf`	Transformers, parallel computation, and logarithmic depth. ICML Clayton Sanford, Daniel Hsu, Matus Telgarsky
2024	J	`jnl`	Transformers, parallel computation, and logarithmic depth. CoRR Clayton Sanford, Daniel Hsu, Matus Telgarsky
2023	A*	`conf`	Feature selection and low test error in shallow low-rotation ReLU networks. ICLR Matus Telgarsky
2023	A*	`conf`	On Achieving Optimal Adversarial Test Error. ICLR Justin D. Li, Matus Telgarsky
2023	J	`jnl`	On Achieving Optimal Adversarial Test Error. CoRR Justin D. Li, Matus Telgarsky
2023	A*	`conf`	Representational Strengths and Limitations of Transformers. NeurIPS Clayton Sanford, Daniel J. Hsu, Matus Telgarsky
2023	J	`jnl`	Representational Strengths and Limitations of Transformers. CoRR Clayton Sanford, Daniel Hsu, Matus Telgarsky
2022	A*	`conf`	Actor-critic is implicitly biased towards high entropy optimal policies. ICLR Yuzheng Hu, Ziwei Ji, Matus Telgarsky
2022	J	`jnl`	Convex Analysis at Infinity: An Introduction to Astral Space. CoRR Miroslav Dudík, Ziwei Ji, Robert E. Schapire, Matus Telgarsky
2022	J	`jnl`	Feature selection with gradient descent on two-layer networks in low-rotation regimes. CoRR Matus Telgarsky
2022	A*	`conf`	Stochastic linear optimization never overfits with quadratically-bounded losses on general data. COLT Matus Telgarsky
2022	J	`jnl`	Stochastic linear optimization never overfits with quadratically-bounded losses on general data. CoRR Matus Telgarsky
2021	J	`jnl`	Actor-critic is implicitly biased towards high entropy optimal policies. CoRR Yuzheng Hu, Ziwei Ji, Matus Telgarsky
2021	B	`conf`	Characterizing the implicit bias via a primal-dual analysis. ALT Ziwei Ji, Matus Telgarsky
2021	A*	`conf`	Early-stopped neural networks are consistent. NeurIPS Ziwei Ji, Justin D. Li, Matus Telgarsky
2021	J	`jnl`	Early-stopped neural networks are consistent. CoRR Ziwei Ji, Justin D. Li, Matus Telgarsky
2021	J	`jnl`	Fast Margin Maximization via Dual Acceleration. CoRR Ziwei Ji, Nathan Srebro, Matus Telgarsky
2021	A*	`conf`	Fast margin maximization via dual acceleration. ICML Ziwei Ji, Nathan Srebro, Matus Telgarsky
2021	A*	`conf`	Generalization bounds via distillation. ICLR Daniel Hsu, Ziwei Ji, Matus Telgarsky, Lan Wang
2021	J	`jnl`	Generalization bounds via distillation. CoRR Daniel Hsu, Ziwei Ji, Matus Telgarsky, Lan Wang
2020	A*	`conf`	Directional convergence and alignment in deep learning. NeurIPS Ziwei Ji, Matus Telgarsky
2020	J	`jnl`	Directional convergence and alignment in deep learning. CoRR Ziwei Ji, Matus Telgarsky
2020	A*	`conf`	Gradient descent follows the regularization path for general losses. COLT Ziwei Ji, Miroslav Dudík, Robert E. Schapire, Matus Telgarsky
2020	J	`jnl`	Gradient descent follows the regularization path for general losses. CoRR Ziwei Ji, Miroslav Dudík, Robert E. Schapire, Matus Telgarsky
2020	A*	`conf`	Neural tangent kernels, transportation mappings, and universal approximation. ICLR Ziwei Ji, Matus Telgarsky, Ruicheng Xian
2020	A*	`conf`	Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks. ICLR Ziwei Ji, Matus Telgarsky
2019	A*	`conf`	A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization. ICML Yucheng Chen, Matus Telgarsky, Chao Zhang, Bolton Bailey, Daniel Hsu, Jian Peng
2019	J	`jnl`	A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization. CoRR Yucheng Chen, Matus Telgarsky, Chao Zhang, Bolton Bailey, Daniel Hsu, Jian Peng
2019	J	`jnl`	A refined primal-dual analysis of the implicit bias. CoRR Ziwei Ji, Matus Telgarsky
2019	—	`conf`	Gradient descent aligns the layers of deep linear networks. ICLR (Poster) Ziwei Ji, Matus Telgarsky
2019	J	`jnl`	Neural tangent kernels, transportation mappings, and universal approximation. CoRR Ziwei Ji, Matus Telgarsky, Ruicheng Xian
2019	J	`jnl`	Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks. CoRR Ziwei Ji, Matus Telgarsky
2019	A*	`conf`	The implicit bias of gradient descent on nonseparable data. COLT Ziwei Ji, Matus Telgarsky
2018	J	`jnl`	Gradient descent aligns the layers of deep linear networks. CoRR Ziwei Ji, Matus Telgarsky
2018	J	`jnl`	Risk and parameter convergence of logistic regression. CoRR Ziwei Ji, Matus Telgarsky
2018	A*	`conf`	Size-Noise Tradeoffs in Generative Networks. NeurIPS Bolton Bailey, Matus Telgarsky
2018	J	`jnl`	Size-Noise Tradeoffs in Generative Networks. CoRR Bolton Bailey, Matus Telgarsky
2018	—	`conf`	Social Welfare and Profit Maximization from Revealed Preferences. WINE Ziwei Ji, Ruta Mehta, Matus Telgarsky
2017	A*	`conf`	Neural Networks and Rational Functions. ICML Matus Telgarsky
2017	J	`jnl`	Neural networks and rational functions. CoRR Matus Telgarsky
2017	A*	`conf`	Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis. COLT Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky
2017	J	`jnl`	Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis. CoRR Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky
2017	J	`jnl`	Social Welfare and Profit Maximization from Revealed Preferences. CoRR Ziwei Ji, Ruta Mehta, Matus Telgarsky
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
2016	J	`jnl`	Benefits of depth in neural networks. CoRR Matus Telgarsky
2016	J	`jnl`	Greedy bi-criteria approximations for k-medians and k-means. CoRR Daniel J. Hsu, Matus Telgarsky
2016	A*	`conf`	Rate of Price Discovery in Iterative Combinatorial Auctions. EC Jacob D. Abernethy, Sébastien Lahaie, Matus Telgarsky
2016	A*	`conf`	benefits of depth in neural networks. COLT Matus Telgarsky
2015	A*	`conf`	Convex Risk Minimization and Conditional Probability Estimation. COLT Matus Telgarsky, Miroslav Dudík
2015	J	`jnl`	Convex Risk Minimization and Conditional Probability Estimation. CoRR Matus Telgarsky, Miroslav Dudík, Robert E. Schapire
2015	J	`jnl`	Rate of Price Discovery in Iterative Combinatorial Auctions. CoRR Jacob D. Abernethy, Sébastien Lahaie, Matus Telgarsky
2015	J	`jnl`	Representation Benefits of Deep Feedforward Networks. CoRR Matus Telgarsky
2015	B	`conf`	Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT). ALT Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2014	—	`conf`	Scalable Non-linear Learning with Adaptive Polynomial Expansions. NIPS Alekh Agarwal, Alina Beygelzimer, Daniel J. Hsu, John Langford, Matus Telgarsky
2014	J	`jnl`	Scalable Nonlinear Learning with Adaptive Polynomial Expansions. CoRR Alekh Agarwal, Alina Beygelzimer, Daniel J. Hsu, John Langford, Matus Telgarsky
2014	J	`jnl`	Tensor decompositions for learning latent variable models. J. Mach. Learn. Res. Animashree Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2013	J	`jnl`	Boosting with the Logistic Loss is Consistent CoRR Matus Telgarsky
2013	A*	`conf`	Boosting with the Logistic Loss is Consistent. COLT Matus Telgarsky
2013	J	`jnl`	Dirichlet draws are sparse with high probability CoRR Matus Telgarsky
2013	—	`—`	Duality and Data Dependence in Boosting /. Matus Telgarsky
2013	J	`jnl`	Margins, Shrinkage, and Boosting CoRR Matus Telgarsky
2013	—	`conf`	Margins, Shrinkage, and Boosting. ICML (2) Matus Telgarsky
2013	—	`conf`	Moment-based Uniform Deviation Bounds for NIPS Matus Telgarsky, Sanjoy Dasgupta
2013	J	`jnl`	Moment-based Uniform Deviation Bounds for $k$-means and Friends. CoRR Matus Telgarsky, Sanjoy Dasgupta
2012	J	`jnl`	A Primal-Dual Convergence Analysis of Boosting. J. Mach. Learn. Res. Matus Telgarsky
2012	A*	`conf`	Agglomerative Bregman Clustering. ICML Matus Telgarsky, Sanjoy Dasgupta
2012	J	`jnl`	Statistical Consistency of Finite-dimensional Unregularized Linear Classification CoRR Matus Telgarsky
2012	J	`jnl`	Tensor decompositions for learning latent variable models CoRR Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
2011	J	`jnl`	Blackwell Approachability and Minimax Theory CoRR Matus Telgarsky
2011	J	`jnl`	The Convergence Rate of AdaBoost and Friends CoRR Matus Telgarsky
2011	—	`conf`	The Fast Convergence of Boosting. NIPS Matus Telgarsky
2010	A	`conf`	Hartigan's Method: k-means Clustering without Voronoi. AISTATS Matus Telgarsky, Andrea Vattani
2007	—	`conf`	Signal Decomposition using Multiscale Admixture Models. ICASSP (2) Matus Telgarsky, John D. Lafferty