Ohad Shamir - RankMe

248 papers A* 84A 8B 4C 1Misc 1Journal 131Unranked 18

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Limitations of SGD for Multi-Index Models Beyond Statistical Queries. CoRR Daniel Barzilai, Ohad Shamir
2025	J	`jnl`	Are Convex Optimization Curves Convex? CoRR Guy Barzilai, Ohad Shamir, Moslem Zamani
2025	J	`jnl`	Are Convex Optimization Curves Convex? Trans. Mach. Learn. Res. Guy Barzilai, Ohad Shamir, Moslem Zamani
2025	J	`jnl`	Hardness of Learning Fixed Parities with Neural Networks. CoRR Itamar Shoshani, Ohad Shamir
2025	A*	`conf`	Logarithmic Width Suffices for Robust Memorization. COLT Amitsour Egosi, Gilad Yehudai, Ohad Shamir
2025	J	`jnl`	Logarithmic Width Suffices for Robust Memorization. CoRR Amitsour Egosi, Gilad Yehudai, Ohad Shamir
2025	J	`jnl`	Overfitting Regimes of Nadaraya-Watson Interpolators. CoRR Daniel Barzilai, Guy Kornowski, Ohad Shamir
2025	A*	`conf`	The Oracle Complexity of Simplex-based Matrix Games: Linear Separability and Nash Equilibria. COLT Guy Kornowski, Ohad Shamir
2025	J	`jnl`	When Models Don't Collapse: On the Consistency of Iterative MLE. CoRR Daniel Barzilai, Ohad Shamir
2024	J	`jnl`	An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization. J. Mach. Learn. Res. Guy Kornowski, Ohad Shamir
2024	A*	`conf`	Depth Separation in Norm-Bounded Infinite-Width Neural Networks. COLT Suzanna Parkinson, Greg Ongie, Rebecca Willett, Ohad Shamir, Nathan Srebro
2024	J	`jnl`	Depth Separation in Norm-Bounded Infinite-Width Neural Networks. CoRR Suzanna Parkinson, Greg Ongie, Rebecca Willett, Ohad Shamir, Nathan Srebro
2024	A*	`conf`	Generalization in Kernel Regression Under Realistic Assumptions. ICML Daniel Barzilai, Ohad Shamir
2024	J	`jnl`	On the Hardness of Meaningful Local Guarantees in Nonsmooth Nonconvex Optimization. CoRR Guy Kornowski, Swati Padmanabhan, Ohad Shamir
2024	A*	`conf`	Open Problem: Anytime Convergence Rate of Gradient Descent. COLT Guy Kornowski, Ohad Shamir
2024	J	`jnl`	Open Problem: Anytime Convergence Rate of Gradient Descent. CoRR Guy Kornowski, Ohad Shamir
2024	J	`jnl`	Simple Relative Deviation Bounds for Covariance and Gram Matrices. CoRR Daniel Barzilai, Ohad Shamir
2024	J	`jnl`	The Oracle Complexity of Simplex-based Matrix Games: Linear Separability and Nash Equilibria. CoRR Guy Kornowski, Ohad Shamir
2023	A*	`conf`	Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance. NeurIPS Nikita Kornilov, Ohad Shamir, Aleksandr V. Lobanov, Darina Dvinskikh, Alexander V. Gasnikov, Innokentiy Shibaev, Eduard Gorbunov, Samuel Horváth
2023	J	`jnl`	An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization. CoRR Guy Kornowski, Ohad Shamir
2023	A*	`conf`	Deterministic Nonsmooth Nonconvex Optimization. COLT Michael I. Jordan, Guy Kornowski, Tianyi Lin, Ohad Shamir, Manolis Zampetakis
2023	J	`jnl`	Deterministic Nonsmooth Nonconvex Optimization. CoRR Michael I. Jordan, Guy Kornowski, Tianyi Lin, Ohad Shamir, Manolis Zampetakis
2023	A*	`conf`	From Tempered to Benign Overfitting in ReLU Neural Networks. NeurIPS Guy Kornowski, Gilad Yehudai, Ohad Shamir
2023	J	`jnl`	From Tempered to Benign Overfitting in ReLU Neural Networks. CoRR Guy Kornowski, Gilad Yehudai, Ohad Shamir
2023	J	`jnl`	Generalization in Kernel Regression Under Realistic Assumptions. CoRR Daniel Barzilai, Ohad Shamir
2023	B	`conf`	Implicit Regularization Towards Rank Minimization in ReLU Networks. ALT Nadav Timor, Gal Vardi, Ohad Shamir
2023	A*	`conf`	Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks. NeurIPS Roey Magen, Ohad Shamir
2023	J	`jnl`	Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks. CoRR Roey Magen, Ohad Shamir
2023	J	`jnl`	The Implicit Bias of Benign Overfitting. J. Mach. Learn. Res. Ohad Shamir
2022	Misc	`conf`	Elephant in the Room: Non-Smooth Non-Convex Optimization. ISAIM Ohad Shamir
2022	A*	`conf`	Gradient Methods Provably Converge to Non-Robust Networks. NeurIPS Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	J	`jnl`	Gradient Methods Provably Converge to Non-Robust Networks. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	J	`jnl`	Implicit Regularization Towards Rank Minimization in ReLU Networks. CoRR Nadav Timor, Gal Vardi, Ohad Shamir
2022	A*	`conf`	On Margin Maximization in Linear and ReLU Networks. NeurIPS Gal Vardi, Ohad Shamir, Nati Srebro
2022	J	`jnl`	On the Complexity of Finding Small Subgradients in Nonsmooth Optimization. CoRR Guy Kornowski, Ohad Shamir
2022	A*	`conf`	On the Optimal Memorization Power of ReLU Neural Networks. ICLR Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	J	`jnl`	Oracle Complexity in Nonsmooth Nonconvex Optimization. J. Mach. Learn. Res. Guy Kornowski, Ohad Shamir
2022	A*	`conf`	Reconstructing Training Data From Trained Neural Networks. NeurIPS Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani
2022	J	`jnl`	Reconstructing Training Data from Trained Neural Networks. CoRR Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani
2022	A*	`conf`	The Implicit Bias of Benign Overfitting. COLT Ohad Shamir
2022	J	`jnl`	The Implicit Bias of Benign Overfitting. CoRR Ohad Shamir
2022	A*	`conf`	The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication (Extended Abstract). IJCAI Blake E. Woodworth, Brian Bullins, Ohad Shamir, Nathan Srebro
2022	A*	`conf`	The Sample Complexity of One-Hidden-Layer Neural Networks. NeurIPS Gal Vardi, Ohad Shamir, Nati Srebro
2022	J	`jnl`	The Sample Complexity of One-Hidden-Layer Neural Networks. CoRR Gal Vardi, Ohad Shamir, Nathan Srebro
2022	A*	`conf`	Width is Less Important than Depth in ReLU Neural Networks. COLT Gal Vardi, Gilad Yehudai, Ohad Shamir
2022	J	`jnl`	Width is Less Important than Depth in ReLU Neural Networks. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	A*	`conf`	A Stochastic Newton Algorithm for Distributed Convex Optimization. NeurIPS Brian Bullins, Kumar Kshitij Patel, Ohad Shamir, Nathan Srebro, Blake E. Woodworth
2021	J	`jnl`	A Stochastic Newton Algorithm for Distributed Convex Optimization. CoRR Brian Bullins, Kumar Kshitij Patel, Ohad Shamir, Nathan Srebro, Blake E. Woodworth
2021	J	`jnl`	Convergence Results For Q-Learning With Experience Replay. CoRR Liran Szlak, Ohad Shamir
2021	J	`jnl`	Gradient Methods Never Overfit On Separable Data. J. Mach. Learn. Res. Ohad Shamir
2021	A*	`conf`	Implicit Regularization in ReLU Networks with the Square Loss. COLT Gal Vardi, Ohad Shamir
2021	A*	`conf`	Learning a Single Neuron with Bias Using Gradient Descent. NeurIPS Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	J	`jnl`	Learning a Single Neuron with Bias Using Gradient Descent. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	J	`jnl`	On Margin Maximization in Linear and ReLU Networks. CoRR Gal Vardi, Ohad Shamir, Nathan Srebro
2021	J	`jnl`	On the Optimal Memorization Power of ReLU Neural Networks. CoRR Gal Vardi, Gilad Yehudai, Ohad Shamir
2021	A*	`conf`	Oracle Complexity in Nonsmooth Nonconvex Optimization. NeurIPS Guy Kornowski, Ohad Shamir
2021	J	`jnl`	Oracle Complexity in Nonsmooth Nonconvex Optimization. CoRR Guy Kornowski, Ohad Shamir
2021	A*	`conf`	Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems. NeurIPS Itay Safran, Ohad Shamir
2021	J	`jnl`	Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems. CoRR Itay Safran, Ohad Shamir
2021	J	`jnl`	Replay For Safety. CoRR Liran Szlak, Ohad Shamir
2021	A*	`conf`	Size and Depth Separation in Approximating Benign Functions with Neural Networks. COLT Gal Vardi, Daniel Reichman, Toniann Pitassi, Ohad Shamir
2021	J	`jnl`	Size and Depth Separation in Approximating Natural Functions with Neural Networks. CoRR Gal Vardi, Daniel Reichman, Toniann Pitassi, Ohad Shamir
2021	A*	`conf`	The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. COLT Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2021	J	`jnl`	The Connection Between Approximation, Depth Separation and Learnability in Neural Networks. CoRR Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2021	A*	`conf`	The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks. COLT Itay Safran, Gilad Yehudai, Ohad Shamir
2021	A*	`conf`	The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication. COLT Blake E. Woodworth, Brian Bullins, Ohad Shamir, Nathan Srebro
2021	J	`jnl`	The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication. CoRR Blake E. Woodworth, Brian Bullins, Ohad Shamir, Nathan Srebro
2020	B	`conf`	A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates. ALT Yossi Arjevani, Ohad Shamir, Nathan Srebro
2020	J	`jnl`	Can We Find Near-Approximately-Stationary Points of Nonsmooth Nonconvex Functions? CoRR Ohad Shamir
2020	J	`jnl`	Gradient Methods Never Overfit On Separable Data. CoRR Ohad Shamir
2020	J	`jnl`	High-Order Oracle Complexity of Smooth and Strongly Convex Optimization. CoRR Guy Kornowski, Ohad Shamir
2020	A*	`conf`	How Good is SGD with Random Shuffling? COLT Itay Safran, Ohad Shamir
2020	J	`jnl`	Implicit Regularization in ReLU Networks with the Square Loss. CoRR Gal Vardi, Ohad Shamir
2020	A*	`conf`	Is Local SGD Better than Minibatch SGD? ICML Blake E. Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro
2020	J	`jnl`	Is Local SGD Better than Minibatch SGD? CoRR Blake E. Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro
2020	A*	`conf`	Learning a Single Neuron with Gradient Methods. COLT Gilad Yehudai, Ohad Shamir
2020	J	`jnl`	Learning a Single Neuron with Gradient Methods. CoRR Gilad Yehudai, Ohad Shamir
2020	A*	`conf`	Neural Networks with Small Weights and Depth-Separation Barriers. NeurIPS Gal Vardi, Ohad Shamir
2020	J	`jnl`	Neural Networks with Small Weights and Depth-Separation Barriers. CoRR Gal Vardi, Ohad Shamir
2020	J	`jnl`	Neural Networks with Small Weights and Depth-Separation Barriers. Electron. Colloquium Comput. Complex. Gal Vardi, Ohad Shamir
2020	A*	`conf`	Proving the Lottery Ticket Hypothesis: Pruning is All You Need. ICML Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2020	J	`jnl`	Proving the Lottery Ticket Hypothesis: Pruning is All You Need. CoRR Eran Malach, Gilad Yehudai, Shai Shalev-Shwartz, Ohad Shamir
2020	A*	`conf`	The Complexity of Finding Stationary Points with Stochastic Gradient Descent. ICML Yoel Drori, Ohad Shamir
2020	J	`jnl`	The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks. CoRR Itay Safran, Gilad Yehudai, Ohad Shamir
2019	A*	`conf`	Depth Separations in Neural Networks: What is Actually Being Separated? COLT Itay Safran, Ronen Eldan, Ohad Shamir
2019	J	`jnl`	Depth Separations in Neural Networks: What is Actually Being Separated? CoRR Itay Safran, Ronen Eldan, Ohad Shamir
2019	A*	`conf`	Exponential Convergence Time of Gradient Descent for One-Dimensional Deep Linear Neural Networks. COLT Ohad Shamir
2019	J	`jnl`	How Good is SGD with Random Shuffling? CoRR Itay Safran, Ohad Shamir
2019	A*	`conf`	On the Power and Limitations of Random Features for Understanding Neural Networks. NeurIPS Gilad Yehudai, Ohad Shamir
2019	J	`jnl`	On the Power and Limitations of Random Features for Understanding Neural Networks. CoRR Gilad Yehudai, Ohad Shamir
2019	J	`jnl`	Oracle complexity of second-order methods for smooth convex optimization. Math. Program. Yossi Arjevani, Ohad Shamir, Ron Shiff
2019	A*	`conf`	Space lower bounds for linear prediction in the streaming model. COLT Yuval Dagan, Gil Kur, Ohad Shamir
2019	J	`jnl`	Space lower bounds for linear prediction. CoRR Yuval Dagan, Gil Kur, Ohad Shamir
2019	J	`jnl`	The Complexity of Finding Stationary Points with Stochastic Gradient Descent. CoRR Yoel Drori, Ohad Shamir
2019	A*	`conf`	The Complexity of Making the Gradient Small in Stochastic Convex Optimization. COLT Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake E. Woodworth
2019	J	`jnl`	The Complexity of Making the Gradient Small in Stochastic Convex Optimization. CoRR Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake E. Woodworth
2018	J	`jnl`	A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates. CoRR Yossi Arjevani, Ohad Shamir, Nathan Srebro
2018	A*	`conf`	Are ResNets Provably Better than Linear Predictors? NeurIPS Ohad Shamir
2018	J	`jnl`	Are ResNets Provably Better than Linear Predictors? CoRR Ohad Shamir
2018	B	`conf`	Bandit Regret Scaling with the Effective Loss Range. ALT Nicolò Cesa-Bianchi, Ohad Shamir
2018	A*	`conf`	Detecting Correlations with Little Memory and Communication. COLT Yuval Dagan, Ohad Shamir
2018	J	`jnl`	Detecting Correlations with Little Memory and Communication. CoRR Yuval Dagan, Ohad Shamir
2018	J	`jnl`	Distribution-Specific Hardness of Learning Neural Networks. J. Mach. Learn. Res. Ohad Shamir
2018	J	`jnl`	Exponential Convergence Time of Gradient Descent for One-Dimensional Deep Linear Neural Networks. CoRR Ohad Shamir
2018	A*	`conf`	Global Non-convex Optimization with Discretized Diffusions. NeurIPS Murat A. Erdogdu, Lester Mackey, Ohad Shamir
2018	J	`jnl`	Global Non-convex Optimization with Discretized Diffusions. CoRR Murat A. Erdogdu, Lester Mackey, Ohad Shamir
2018	A*	`conf`	Size-Independent Sample Complexity of Neural Networks. COLT Noah Golowich, Alexander Rakhlin, Ohad Shamir
2018	A*	`conf`	Spurious Local Minima are Common in Two-Layer ReLU Neural Networks. ICML Itay Safran, Ohad Shamir
2017	J	`jnl`	An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback. J. Mach. Learn. Res. Ohad Shamir
2017	J	`jnl`	Bandit Regret Scaling with the Effective Loss Range. CoRR Nicolò Cesa-Bianchi, Ohad Shamir
2017	A*	`conf`	Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis. ICML Dan Garber, Ohad Shamir, Nathan Srebro
2017	J	`jnl`	Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis. CoRR Dan Garber, Ohad Shamir, Nathan Srebro
2017	A*	`conf`	Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks. ICML Itay Safran, Ohad Shamir
2017	J	`jnl`	Failures of Deep Learning. CoRR Shai Shalev-Shwartz, Ohad Shamir, Shaked Shammah
2017	A*	`conf`	Failures of Gradient-Based Deep Learning. ICML Shai Shalev-Shwartz, Ohad Shamir, Shaked Shammah
2017	J	`jnl`	Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback. SIAM J. Comput. Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile, Shie Mannor, Yishay Mansour, Ohad Shamir
2017	A*	`conf`	Online Learning with Local Permutations and Delayed Feedback. ICML Ohad Shamir, Liran Szlak
2017	J	`jnl`	Online Learning with Local Permutations and Delayed Feedback. CoRR Ohad Shamir, Liran Szlak
2017	A*	`conf`	Oracle Complexity of Second-Order Methods for Finite-Sum Problems. ICML Yossi Arjevani, Ohad Shamir
2017	A*	`conf`	Preface: Conference on Learning Theory (COLT), 2017. COLT Satyen Kale, Ohad Shamir
2017	A*	`ed.`	Proceedings of the 30th Conference on Learning Theory, COLT 2017, Amsterdam, The Netherlands, 7-10 July 2017 COLT Satyen Kale, Ohad Shamir
2017	J	`jnl`	Size-Independent Sample Complexity of Neural Networks. CoRR Noah Golowich, Alexander Rakhlin, Ohad Shamir
2017	J	`jnl`	Spurious Local Minima are Common in Two-Layer ReLU Neural Networks. CoRR Itay Safran, Ohad Shamir
2017	J	`jnl`	Weight Sharing is Crucial to Succesful Optimization. CoRR Shai Shalev-Shwartz, Ohad Shamir, Shaked Shammah
2016	A*	`conf`	Convergence of Stochastic Gradient Descent for PCA. ICML Ohad Shamir
2016	J	`jnl`	Depth Separation in ReLU Networks for Approximating Smooth Non-Linear Functions. CoRR Itay Safran, Ohad Shamir
2016	—	`conf`	Dimension-Free Iteration Complexity of Finite Sum Optimization Problems. NIPS Yossi Arjevani, Ohad Shamir
2016	J	`jnl`	Dimension-Free Iteration Complexity of Finite Sum Optimization Problems. CoRR Yossi Arjevani, Ohad Shamir
2016	J	`jnl`	Distribution-Specific Hardness of Learning Neural Networks. CoRR Ohad Shamir
2016	A*	`conf`	Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity. ICML Ohad Shamir
2016	A*	`conf`	Multi-Player Bandits - a Musical Chairs Approach. ICML Jonathan Rosenski, Ohad Shamir, Liran Szlak
2016	J	`jnl`	On Lower and Upper Bounds in Smooth and Strongly Convex Optimization. J. Mach. Learn. Res. Yossi Arjevani, Shai Shalev-Shwartz, Ohad Shamir
2016	A*	`conf`	On the Iteration Complexity of Oblivious First-Order Optimization Algorithms. ICML Yossi Arjevani, Ohad Shamir
2016	J	`jnl`	On the Iteration Complexity of Oblivious First-Order Optimization Algorithms. CoRR Yossi Arjevani, Ohad Shamir
2016	A*	`conf`	On the Quality of the Initial Basin in Overspecified Neural Networks. ICML Itay Safran, Ohad Shamir
2016	J	`jnl`	Oracle Complexity of Second-Order Methods for Finite-Sum Problems. CoRR Yossi Arjevani, Ohad Shamir
2016	A*	`ed.`	Proceedings of the 29th Conference on Learning Theory, COLT 2016, New York, USA, June 23-26, 2016 COLT Vitaly Feldman, Alexander Rakhlin, Ohad Shamir
2016	A*	`conf`	The Power of Depth for Feedforward Neural Networks. COLT Ronen Eldan, Ohad Shamir
2016	J	`jnl`	Unified Algorithms for Online Learning and Competitive Analysis. Math. Oper. Res. Niv Buchbinder, Shahar Chen, Joseph Naor, Ohad Shamir
2016	—	`conf`	Without-Replacement Sampling for Stochastic Gradient Methods. NIPS Ohad Shamir
2016	J	`jnl`	Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization. CoRR Ohad Shamir
2015	A*	`conf`	A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate. ICML Ohad Shamir
2015	J	`jnl`	An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback. CoRR Ohad Shamir
2015	A*	`conf`	Attribute Efficient Linear Regression with Distribution-Dependent Sampling. ICML Doron Kukliansky, Ohad Shamir
2015	—	`conf`	Communication Complexity of Distributed Convex Learning and Optimization. NIPS Yossi Arjevani, Ohad Shamir
2015	J	`jnl`	Communication Complexity of Distributed Convex Learning and Optimization. CoRR Yossi Arjevani, Ohad Shamir
2015	J	`jnl`	Convergence of Stochastic Gradient Descent for PCA. CoRR Ohad Shamir
2015	J	`jnl`	Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity. CoRR Ohad Shamir
2015	A	`conf`	Graph Approximation and Clustering on a Budget. AISTATS Ethan Fetaya, Ohad Shamir, Shimon Ullman
2015	J	`jnl`	Multi-Player Bandits - a Musical Chairs Approach. CoRR Jonathan Rosenski, Ohad Shamir, Liran Szlak
2015	J	`jnl`	On Lower and Upper Bounds for Smooth and Strongly Convex Optimization Problems. CoRR Yossi Arjevani, Shai Shalev-Shwartz, Ohad Shamir
2015	A*	`conf`	On the Complexity of Bandit Linear Optimization. COLT Ohad Shamir
2015	A*	`conf`	On the Complexity of Learning with Kernels. COLT Nicolò Cesa-Bianchi, Yishay Mansour, Ohad Shamir
2015	J	`jnl`	On the Quality of the Initial Basin in Overspecified Neural Networks. CoRR Itay Safran, Ohad Shamir
2015	J	`jnl`	The Power of Depth for Feedforward Neural Networks. CoRR Ronen Eldan, Ohad Shamir
2015	J	`jnl`	The sample complexity of learning linear predictors with the squared loss. J. Mach. Learn. Res. Ohad Shamir
2014	J	`jnl`	A Stochastic PCA Algorithm with an Exponential Convergence Rate. CoRR Ohad Shamir
2014	J	`jnl`	Attribute Efficient Linear Regression with Data-Dependent Sampling. CoRR Doron Kukliansky, Ohad Shamir
2014	A*	`conf`	Communication-Efficient Distributed Optimization using an Approximate Newton-type Method. ICML Ohad Shamir, Nathan Srebro, Tong Zhang
2014	—	`conf`	Distributed stochastic optimization and learning. Allerton Ohad Shamir, Nathan Srebro
2014	—	`conf`	Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation. NIPS Ohad Shamir
2014	J	`jnl`	Graph Approximation and Clustering on a Budget. CoRR Ethan Fetaya, Ohad Shamir, Shimon Ullman
2014	J	`jnl`	Matrix completion with the trace norm: learning, bounding, and transducing. J. Mach. Learn. Res. Ohad Shamir, Shai Shalev-Shwartz
2014	J	`jnl`	Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback. CoRR Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile, Shie Mannor, Yishay Mansour, Ohad Shamir
2014	J	`jnl`	On the Complexity of Bandit Linear Optimization. CoRR Ohad Shamir
2014	J	`jnl`	On the Complexity of Learning with Kernels. CoRR Nicolò Cesa-Bianchi, Yishay Mansour, Ohad Shamir
2014	—	`conf`	On the Computational Efficiency of Training Neural Networks. NIPS Roi Livni, Shai Shalev-Shwartz, Ohad Shamir
2014	J	`jnl`	On the Computational Efficiency of Training Neural Networks. CoRR Roi Livni, Shai Shalev-Shwartz, Ohad Shamir
2014	—	`conf`	On-demand, Spot, or Both: Dynamic Resource Allocation for Executing Batch Jobs in the Cloud. ICAC Ishai Menache, Ohad Shamir, Navendu Jain
2014	J	`jnl`	The Sample Complexity of Learning Linear Predictors with the Squared Loss. CoRR Ohad Shamir
2013	J	`jnl`	A Provably Efficient Algorithm for Training Deep Networks CoRR Roi Livni, Shai Shalev-Shwartz, Ohad Shamir
2013	C	`conf`	Accurate Profiling of Microbial Communities from Massively Parallel Sequencing Using Convex Optimization. SPIRE Or Zuk, Amnon Amir, Amit Zeisel, Ohad Shamir, Noam Shental
2013	J	`jnl`	Accurate Profiling of Microbial Communities from Massively Parallel Sequencing using Convex Optimization. CoRR Or Zuk, Amnon Amir, Amit Zeisel, Ohad Shamir, Noam Shental
2013	J	`jnl`	Communication Efficient Distributed Optimization using an Approximate Newton-type Method. CoRR Ohad Shamir, Nathan Srebro, Tong Zhang
2013	—	`conf`	Efficient Transductive Online Learning via Randomized Rounding. Empirical Inference Nicolò Cesa-Bianchi, Ohad Shamir
2013	J	`jnl`	Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation. CoRR Ohad Shamir
2013	A	`conf`	Localization and Adaptation in Online Learning. AISTATS Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
2013	A*	`conf`	On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization. COLT Ohad Shamir
2013	J	`jnl`	Online Learning for Time Series Prediction CoRR Oren Anava, Elad Hazan, Shie Mannor, Ohad Shamir
2013	A*	`conf`	Online Learning for Time Series Prediction. COLT Oren Anava, Elad Hazan, Shie Mannor, Ohad Shamir
2013	J	`jnl`	Online Learning with Switching Costs and Other Adaptive Adversaries CoRR Nicolò Cesa-Bianchi, Ofer Dekel, Ohad Shamir
2013	—	`conf`	Online Learning with Switching Costs and Other Adaptive Adversaries. NIPS Nicolò Cesa-Bianchi, Ofer Dekel, Ohad Shamir
2013	A*	`conf`	Probabilistic Label Trees for Efficient Large Scale Image Classification. CVPR Baoyuan Liu, Fereshteh Sadeghi, Marshall F. Tappen, Ohad Shamir, Ce Liu
2013	—	`conf`	Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes. ICML (1) Ohad Shamir, Tong Zhang
2012	J	`jnl`	Decoupling Exploration and Exploitation in Multi-Armed Bandits CoRR Orly Avner, Shie Mannor, Ohad Shamir
2012	A*	`conf`	Decoupling Exploration and Exploitation in Multi-Armed Bandits. ICML Orly Avner, Shie Mannor, Ohad Shamir
2012	A	`conf`	Learning from Weak Teachers. AISTATS Ruth Urner, Shai Ben-David, Ohad Shamir
2012	A*	`conf`	Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization. ICML Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
2012	J	`jnl`	On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization CoRR Ohad Shamir
2012	A*	`conf`	Open Problem: Is Averaging Needed for Strongly Convex Stochastic Gradient Descent? COLT Ohad Shamir
2012	J	`jnl`	Optimal Distributed Online Prediction Using Mini-Batches. J. Mach. Learn. Res. Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao
2012	J	`jnl`	Relax and Localize: From Value to Algorithms CoRR Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
2012	—	`conf`	Relax and Randomize : From Value to Algorithms. NIPS Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
2012	J	`jnl`	Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes CoRR Ohad Shamir, Tong Zhang
2012	A	`conf`	There's a Hole in My Data Space: Piecewise Predictors for Heterogeneous Learning Problems. AISTATS Ofer Dekel, Ohad Shamir
2012	A*	`conf`	Unified Algorithms for Online Learning and Competitive Analysis. COLT Niv Buchbinder, Shahar Chen, Joseph Naor, Ohad Shamir
2012	A	`conf`	Using More Data to Speed-up Training Time. AISTATS Shai Shalev-Shwartz, Ohad Shamir, Eran Tromer
2011	J	`jnl`	A Variant of Azuma's Inequality for Martingales with Subgaussian Tails CoRR Ohad Shamir
2011	J	`jnl`	Adaptively Learning the Crowd Kernel CoRR Omer Tamuz, Ce Liu, Serge J. Belongie, Ohad Shamir, Adam Tauman Kalai
2011	A*	`conf`	Adaptively Learning the Crowd Kernel. ICML Omer Tamuz, Ce Liu, Serge J. Belongie, Ohad Shamir, Adam Kalai
2011	J	`jnl`	Better Mini-Batch Algorithms via Accelerated Gradient Methods CoRR Andrew Cotter, Ohad Shamir, Nathan Srebro, Karthik Sridharan
2011	—	`conf`	Better Mini-Batch Algorithms via Accelerated Gradient Methods. NIPS Andrew Cotter, Ohad Shamir, Nati Srebro, Karthik Sridharan
2011	A*	`conf`	Collaborative Filtering with the Trace Norm: Learning, Bounding, and Transducing. COLT Ohad Shamir, Shai Shalev-Shwartz
2011	J	`jnl`	Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression CoRR Sham M. Kakade, Adam Tauman Kalai, Varun Kanade, Ohad Shamir
2011	—	`conf`	Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression. NIPS Sham M. Kakade, Adam Kalai, Varun Kanade, Ohad Shamir
2011	J	`jnl`	Efficient Learning with Partially Observed Attributes. J. Mach. Learn. Res. Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2011	J	`jnl`	Efficient Online Learning via Randomized Rounding CoRR Nicolò Cesa-Bianchi, Ohad Shamir
2011	—	`conf`	Efficient Online Learning via Randomized Rounding. NIPS Nicolò Cesa-Bianchi, Ohad Shamir
2011	J	`jnl`	From Bandits to Experts: On the Value of Side-Observations CoRR Shie Mannor, Ohad Shamir
2011	—	`conf`	From Bandits to Experts: On the Value of Side-Observations. NIPS Shie Mannor, Ohad Shamir
2011	J	`jnl`	Large-Scale Convex Minimization with a Low-Rank Constraint CoRR Shai Shalev-Shwartz, Alon Gonen, Ohad Shamir
2011	A*	`conf`	Large-Scale Convex Minimization with a Low-Rank Constraint. ICML Shai Shalev-Shwartz, Alon Gonen, Ohad Shamir
2011	J	`jnl`	Learning Kernel-Based Halfspaces with the 0-1 Loss. SIAM J. Comput. Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
2011	A*	`conf`	Learning Linear and Kernel Predictors with the 0-1 Loss Function. IJCAI Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
2011	J	`jnl`	Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions CoRR Rina Foygel, Ruslan Salakhutdinov, Ohad Shamir, Nathan Srebro
2011	—	`conf`	Learning with the weighted trace-norm under arbitrary sampling distributions. NIPS Rina Foygel, Ruslan Salakhutdinov, Ohad Shamir, Nati Srebro
2011	J	`jnl`	Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization CoRR Ohad Shamir
2011	J	`jnl`	Online Learning of Noisy Data. IEEE Trans. Inf. Theory Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2011	A*	`conf`	Optimal Distributed Online Prediction. ICML Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao
2011	A*	`conf`	Quantity Makes Quality: Learning with Partial Views. AAAI Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2011	A	`conf`	Spectral Clustering on a Budget. AISTATS Ohad Shamir, Naftali Tishby
2011	J	`jnl`	Using More Data to Speed-up Training Time CoRR Shai Shalev-Shwartz, Ohad Shamir, Eran Tromer
2010	J	`jnl`	Efficient Learning with Partially Observed Attributes CoRR Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2010	A*	`conf`	Efficient Learning with Partially Observed Attributes. ICML Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2010	J	`jnl`	Learnability, Stability and Uniform Convergence. J. Mach. Learn. Res. Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan
2010	A	`conf`	Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity. AISTATS Sham M. Kakade, Ohad Shamir, Karthik Sindharan, Ambuj Tewari
2010	J	`jnl`	Learning Kernel-Based Halfspaces with the Zero-One Loss CoRR Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
2010	A*	`conf`	Learning Kernel-Based Halfspaces with the Zero-One Loss. COLT Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
2010	J	`jnl`	Learning and generalization with the information bottleneck. Theor. Comput. Sci. Ohad Shamir, Sivan Sabato, Naftali Tishby
2010	J	`jnl`	Learning to classify with missing and corrupted features. Mach. Learn. Ofer Dekel, Ohad Shamir, Lin Xiao
2010	A	`conf`	Multiclass-Multilabel Classification with More Classes than Examples. AISTATS Ofer Dekel, Ohad Shamir
2010	—	`—`	On stability in statistical machine learning (עם תקציר בעברית ושער נוסף: על יציבות בלמידה חישובית סטטיסטית.). Ohad Shamir
2010	J	`jnl`	Online Learning of Noisy Data with Kernels CoRR Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2010	A*	`conf`	Online Learning of Noisy Data with Kernels. COLT Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, Ohad Shamir
2010	J	`jnl`	Optimal Distributed Online Prediction using Mini-Batches CoRR Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao
2010	J	`jnl`	Robust Distributed Online Prediction CoRR Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao
2010	J	`jnl`	Stability and model selection in Mach. Learn. Ohad Shamir, Naftali Tishby
2009	A*	`conf`	Good learners for evil teachers. ICML Ofer Dekel, Ohad Shamir
2009	A*	`conf`	Learnability and Stability in the General Learning Setting. COLT Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan
2009	J	`jnl`	Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity CoRR Sham M. Kakade, Ohad Shamir, Karthik Sridharan, Ambuj Tewari
2009	A*	`conf`	Stochastic Convex Optimization. COLT Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan
2009	A*	`conf`	The Complexity of Improperly Learning Large Margin Halfspaces. COLT Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
2009	A*	`conf`	Vox Populi: Collecting High-Quality Labels from a Crowd. COLT Ofer Dekel, Ohad Shamir
2008	B	`conf`	Learning and Generalization with the Information Bottleneck. ALT Ohad Shamir, Sivan Sabato, Naftali Tishby
2008	A*	`conf`	Learning to classify with missing and corrupted features. ICML Ofer Dekel, Ohad Shamir
2008	A*	`conf`	Model Selection and Stability in k-means Clustering. COLT Ohad Shamir, Naftali Tishby
2008	—	`conf`	On the Reliability of Clustering Stability in the Large Sample Regime. NIPS Ohad Shamir, Naftali Tishby
2007	—	`conf`	Cluster Stability for Finite Samples. NIPS Ohad Shamir, Naftali Tishby