Ohad Shamir

发表

Learning a Single Neuron with Gradient Methods pdf

Gilad Yehudai, Ohad Shamir, 2020, COLT 2020.

Learning with the weighted trace-norm under arbitrary sampling distributions

Ohad Shamir, Ruslan Salakhutdinov, Nathan Srebro, 2011, NIPS.

Learning to classify with missing and corrupted features

Ohad Shamir, Lin Xiao, Ofer Dekel, 2008, ICML '08.

The Complexity of Making the Gradient Small in Stochastic Convex Optimization

Ohad Shamir, Nathan Srebro, Karthik Sridharan, 2019, COLT.

New England

Shai Ben-David, Ruth Urner, Ohad Shamir, 1894, Letters from America.

Graph Approximation and Clustering on a Budget pdf

Shimon Ullman, Ohad Shamir, Ethan Fetaya, 2015, AISTATS.

Learning Kernel-Based Halfspaces with the Zero-One Loss

Ohad Shamir, Karthik Sridharan, Shai Shalev-Shwartz, 2010, COLT 2010.

On Lower and Upper Bounds in Smooth and Strongly Convex Optimization

Ohad Shamir, Shai Shalev-Shwartz, Yossi Arjevani, 2016, J. Mach. Learn. Res..

On the Complexity of Bandit Linear Optimization

Ohad Shamir, O. Shamir, 2014, COLT.

A Variant of Azuma's Inequality for Martingales with Subgaussian Tails pdf

Ohad Shamir, 2011, ArXiv.

Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks

Ohad Shamir, Itay Safran, O. Shamir, 2016, ICML.

Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity pdf

Ohad Shamir, O. Shamir, 2015, ICML.

Cluster Stability for Finite Samples

Ohad Shamir, Naftali Tishby, Naftali Tishby, 2007, NIPS.

Learning Kernel-Based Halfspaces with the 0-1 Loss

Ohad Shamir, Karthik Sridharan, Shai Shalev-Shwartz, 2011, SIAM J. Comput..

On the Complexity of Learning with Kernels pdf

Yishay Mansour, Ohad Shamir, Nicolò Cesa-Bianchi, 2014, COLT.

Is Local SGD Better than Minibatch SGD? pdf

Ohad Shamir, Nathan Srebro, Sebastian U. Stich, 2020, ICML.

The sample complexity of learning linear predictors with the squared loss

Ohad Shamir, O. Shamir, 2014, J. Mach. Learn. Res..

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

Gilad Yehudai, Ohad Shamir, Shai Shalev-Shwartz, 2020, ICML.

Learnability, Stability and Uniform Convergence

Ohad Shamir, Nathan Srebro, Karthik Sridharan, 2010, J. Mach. Learn. Res..

Stability and model selection in k-means clustering

Ohad Shamir, Naftali Tishby, Naftali Tishby, 2010, Machine Learning.

Dimension-Free Iteration Complexity of Finite Sum Optimization Problems

Ohad Shamir, Yossi Arjevani, 2016, NIPS.

Without-Replacement Sampling for Stochastic Gradient Methods

Ohad Shamir, O. Shamir, 2016, NIPS.

From Bandits to Experts: On the Value of Side-Observations

Shie Mannor, Ohad Shamir, Shie Mannor, 2011, NIPS.

A Provably Efficient Algorithm for Training Deep Networks pdf

Roi Livni, Ohad Shamir, Shai Shalev-Shwartz, 2013, ArXiv.

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Learning Linear and Kernel Predictors with the 0–1 Loss Function

Ohad Shamir, Karthik Sridharan, Shai Shalev-Shwartz, 2022 .

Vox Populi: Collecting High-Quality Labels from a Crowd

Ohad Shamir, Ofer Dekel, O. Dekel, 2009, COLT.

Detecting Correlations with Little Memory and Communication

Ohad Shamir, Yuval Dagan, O. Shamir, 2018, COLT 2018.

On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization pdf

Ohad Shamir, O. Shamir, Ohad Shamir, 2012, COLT.

Better Mini-Batch Algorithms via Accelerated Gradient Methods

Ohad Shamir, Nathan Srebro, Karthik Sridharan, 2011, NIPS.

Distributed stochastic optimization and learning

Ohad Shamir, Nathan Srebro, Nathan Srebro, 2014, 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Performance estimation of stochastic first-order methods

Ohad Shamir, Yoel Drori, O. Shamir, 2019 .

Attribute Efficient Linear Regression with Data-Dependent Sampling pdf

Ohad Shamir, Doron Kukliansky, 2014, ArXiv.

The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks pdf

Gilad Yehudai, Ohad Shamir, Itay Safran, 2020, ArXiv.

Multi-player bandits: a musical chairs approach

Ohad Shamir, Jonathan Rosenski, Liran Szlak, 2016, ICML 2016.

Learnability and Stability in the General Learning Setting

Ohad Shamir, Nathan Srebro, Karthik Sridharan, 2009, COLT.

Large-Scale Convex Minimization with a Low-Rank Constraint pdf

Ohad Shamir, Shai Shalev-Shwartz, Alon Gonen, 2011, ICML.

Spurious Local Minima are Common in Two-Layer ReLU Neural Networks pdf

Ohad Shamir, Itay Safran, O. Shamir, 2017, ICML.

Oracle complexity of second-order methods for smooth convex optimization

Ohad Shamir, Yossi Arjevani, Ron Shiff, 2017, Mathematical Programming.

Multiclass-Multilabel Classification with More Classes than Examples

Ohad Shamir, Ofer Dekel, O. Dekel, 2010, AISTATS.

Learning to classify with missing and corrupted features

Ohad Shamir, Ofer Dekel, O. Dekel, 2008, ICML.

Robust Distributed Online Prediction pdf

Ohad Shamir, Ran Gilad-Bachrach, Lin Xiao, 2010, ArXiv.

Online Learning for Time Series Prediction

Shie Mannor, Ohad Shamir, Elad Hazan, 2013, COLT.

How Good is SGD with Random Shuffling? pdf

Ohad Shamir, Itay Safran, O. Shamir, 2019, COLT 2019.

Implicit Regularization in ReLU Networks with the Square Loss pdf

Ohad Shamir, Gal Vardi, 2020, ArXiv.

Learning and generalization with the information bottleneck

Ohad Shamir, Naftali Tishby, Sivan Sabato, 2008, Theor. Comput. Sci..

Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization pdf

Ohad Shamir, O. Shamir, 2016, ArXiv.

Probabilistic Label Trees for Efficient Large Scale Image Classification

Ohad Shamir, Ce Liu, Fereshteh Sadeghi, 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

Online Learning with Switching Costs and Other Adaptive Adversaries

Nicolò Cesa-Bianchi, Ohad Shamir, Ofer Dekel, 2013, NIPS.

Attribute Efficient Linear Regression with Distribution-Dependent Sampling

Ohad Shamir, Doron Kukliansky, O. Shamir, 2015, ICML.

On the Iteration Complexity of Oblivious First-Order Optimization Algorithms pdf

Ohad Shamir, Yossi Arjevani, O. Shamir, 2016, ICML.

Quantity Makes Quality: Learning with Partial Views

Ohad Shamir, Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, 2011, AAAI.

On Lower and Upper Bounds for Smooth and Strongly Convex Optimization Problems pdf

Ohad Shamir, Shai Shalev-Shwartz, Yossi Arjevani, 2015, ArXiv.

There's a Hole in My Data Space: Piecewise Predictors for Heterogeneous Learning Problems

Ohad Shamir, Ofer Dekel, O. Dekel, 2012, AISTATS.

Optimal Distributed Online Prediction Using Mini-Batches

Ohad Shamir, Ran Gilad-Bachrach, Lin Xiao, 2010, J. Mach. Learn. Res..

Failures of Deep Learning pdf

Ohad Shamir, Shai Shalev-Shwartz, Shaked Shammah, 2017, ArXiv.

Space lower bounds for linear prediction in the streaming model

Ohad Shamir, Yuval Dagan, Gil Kur, 2019, COLT.

On the Computational Efficiency of Training Neural Networks

Roi Livni, Ohad Shamir, Shai Shalev-Shwartz, 2014, NIPS.

Exponential Convergence Time of Gradient Descent for One-Dimensional Deep Linear Neural Networks

Ohad Shamir, O. Shamir, 2018, COLT.

Communication-Efficient Distributed Optimization using an Approximate Newton-type Method pdf

Ohad Shamir, Tong Zhang, Nathan Srebro, 2013, ICML.

Convergence of Stochastic Gradient Descent for PCA pdf

Ohad Shamir, O. Shamir, 2015, ICML.

Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization pdf

Ohad Shamir, Alexander Rakhlin, Karthik Sridharan, 2011, ICML.

Open Problem: Is Averaging Needed for Strongly Convex Stochastic Gradient Descent?

Ohad Shamir, O. Shamir, 2012, COLT.

Oracle Complexity of Second-Order Methods for Finite-Sum Problems pdf

Ohad Shamir, Yossi Arjevani, O. Shamir, 2016, ICML.

Relax and Randomize : From Value to Algorithms

Ohad Shamir, Karthik Sridharan, Alexander Rakhlin, 2012, NIPS.

On the Reliability of Clustering Stability in the Large Sample Regime

Ohad Shamir, Naftali Tishby, Naftali Tishby, 2008, NIPS.

Failures of Gradient-Based Deep Learning

Ohad Shamir, Shai Shalev-Shwartz, Shaked Shammah, 2017, ICML.

Global Non-convex Optimization with Discretized Diffusions

Ohad Shamir, Murat A. Erdogdu, Lester Mackey, 2018, NeurIPS.

Online Learning with Local Permutations and Delayed Feedback

Ohad Shamir, Liran Szlak, 2017, ICML.

Efficient Learning with Partially Observed Attributes

Ohad Shamir, Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, 2010, ICML.

Depth Separations in Neural Networks: What is Actually Being Separated? pdf

Ohad Shamir, Ronen Eldan, Itay Safran, 2019, Constructive Approximation.

Gradient Methods Never Overfit On Separable Data pdf

Ohad Shamir, O. Shamir, 2020, J. Mach. Learn. Res..

On the Power and Limitations of Random Features for Understanding Neural Networks

Gilad Yehudai, Ohad Shamir, O. Shamir, 2019, NeurIPS.

Preface: Conference on Learning Theory (COLT), 2017

Ohad Shamir, Satyen Kale, O. Shamir, 2017, COLT.

Collaborative Filtering with the Trace Norm: Learning, Bounding, and Transducing

Ohad Shamir, Shai Shalev-Shwartz, 2011, COLT.

Efficient Online Learning via Randomized Rounding

Ohad Shamir, Nicolò Cesa-Bianchi, N. Cesa-Bianchi, 2011, NIPS.

Spectral Clustering on a Budget

Ohad Shamir, Naftali Tishby, 2011, AISTATS.

Using More Data to Speed-up Training Time pdf

Ohad Shamir, Shai Shalev-Shwartz, Eran Tromer, 2011, AISTATS.

Space lower bounds for linear prediction pdf

Ohad Shamir, Yuval Dagan, Gil Kur, 2019, ArXiv.

A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates

Ohad Shamir, Nathan Srebro, Yossi Arjevani, 2018, ALT.

Can We Find Near-Approximately-Stationary Points of Nonsmooth Nonconvex Functions? pdf

Ohad Shamir, O. Shamir, 2020, ArXiv.

Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback

Noga Alon, Shie Mannor, Claudio Gentile, 2014, SIAM J. Comput..

Localization and Adaptation in Online Learning

Ohad Shamir, Karthik Sridharan, Alexander Rakhlin, 2013, AISTATS.

On-demand, Spot, or Both: Dynamic Resource Allocation for Executing Batch Jobs in the Cloud

Ohad Shamir, Navendu Jain, Ishai Menache, 2014, ICAC.

Size-Independent Sample Complexity of Neural Networks

Ohad Shamir, Noah Golowich, Alexander Rakhlin, 2017, COLT.

Decoupling Exploration and Exploitation in Multi-Armed Bandits pdf

Shie Mannor, Ohad Shamir, Orly Avner, 2012, ICML.

Information constraints in distributed and online learning

Ohad Shamir, 2014 .

Distribution-Specific Hardness of Learning Neural Networks

Ohad Shamir, O. Shamir, 2016, J. Mach. Learn. Res..

On the Quality of the Initial Basin in Overspecified Neural Networks

Ohad Shamir, Itay Safran, O. Shamir, 2015, ICML.

Adaptively Learning the Crowd Kernel pdf

Adam Tauman Kalai, Ohad Shamir, Ce Liu, 2011, ICML.

Neural Networks with Small Weights and Depth-Separation Barriers

Ohad Shamir, Gal Vardi, O. Shamir, 2020, Electron. Colloquium Comput. Complex..

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression

Adam Tauman Kalai, Varun Kanade, Ohad Shamir, 2011, NIPS.

Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation

Ohad Shamir, O. Shamir, Ohad Shamir, 2013, NIPS.

Stochastic Convex Optimization

Ohad Shamir, Nathan Srebro, Karthik Sridharan, 2009, COLT.

Learning and generalization with the information bottleneck

Ohad Shamir, Naftali Tishby, Sivan Sabato, 2008, Theoretical Computer Science.

Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis

Ohad Shamir, Nathan Srebro, Dan Garber, 2017, ICML.

An Algorithm for Training Polynomial Networks

Roi Livni, Ohad Shamir, Shai Shalev-Shwartz, 2013, 1304.7045.

A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate pdf

Ohad Shamir, O. Shamir, 2014, ICML.

Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes

Ohad Shamir, Tong Zhang, Tong Zhang, 2012, ICML.

The Power of Depth for Feedforward Neural Networks pdf

Ohad Shamir, Ronen Eldan, O. Shamir, 2015, COLT.

The Complexity of Improperly Learning Large Margin Halfspaces

Ohad Shamir, Karthik Sridharan, Shai Shalev-Shwartz, 2009, COLT.

Communication Complexity of Distributed Convex Learning and Optimization

Ohad Shamir, Yossi Arjevani, O. Shamir, 2015, NIPS.

Depth Separation in ReLU Networks for Approximating Smooth Non-Linear Functions pdf

Ohad Shamir, Itay Safran, O. Shamir, 2016, ArXiv.

Matrix completion with the trace norm: learning, bounding, and transducing

Ohad Shamir, Shai Shalev-Shwartz, S. Shalev-Shwartz, 2014, J. Mach. Learn. Res..

Weight Sharing is Crucial to Succesful Optimization pdf

Ohad Shamir, Shai Shalev-Shwartz, Shaked Shammah, 2017, ArXiv.

Efficient Transductive Online Learning via Randomized Rounding

Ohad Shamir, Nicolò Cesa-Bianchi, N. Cesa-Bianchi, 2011, Empirical Inference.

Unified Algorithms for Online Learning and Competitive Analysis

Joseph Naor, Ohad Shamir, Niv Buchbinder, 2012, COLT.

An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback

Ohad Shamir, O. Shamir, Ohad Shamir, 2015, J. Mach. Learn. Res..

Bandit Regret Scaling with the Effective Loss Range pdf

Ohad Shamir, Nicolò Cesa-Bianchi, N. Cesa-Bianchi, 2017, ALT.

Online Learning of Noisy Data

Nicolò Cesa-Bianchi, Ohad Shamir, Shai Shalev-Shwartz, 2011, IEEE Transactions on Information Theory.

Good learners for evil teachers

Ohad Shamir, Ofer Dekel, O. Dekel, 2009, ICML '09.

The Complexity of Finding Stationary Points with Stochastic Gradient Descent

Ohad Shamir, Yoel Drori, 2020, ICML.

Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity

Ambuj Tewari, Ohad Shamir, Sham M. Kakade, 2009, AISTATS.

Online Learning of Noisy Data with Kernels

Ohad Shamir, Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, 2010, COLT 2010.

Accurate Profiling of Microbial Communities from Massively Parallel Sequencing Using Convex Optimization

Ohad Shamir, Noam Shental, Amnon Amir, 2013, SPIRE.

Relax and Localize: From Value to Algorithms pdf

Ohad Shamir, Karthik Sridharan, Alexander Rakhlin, 2012, ArXiv.

High-Order Oracle Complexity of Smooth and Strongly Convex Optimization pdf

Ohad Shamir, Guy Kornowski, 2020, ArXiv.

Are ResNets Provably Better than Linear Predictors?

Ohad Shamir, O. Shamir, Ohad Shamir, 2018, NeurIPS.

Optimal Distributed Online Prediction

Ohad Shamir, Ran Gilad-Bachrach, Lin Xiao, 2011, ICML.

Size and Depth Separation in Approximating Natural Functions with Neural Networks pdf

Toniann Pitassi, Ohad Shamir, Daniel Reichman, 2021, ArXiv.

On the Optimal Memorization Power of ReLU Neural Networks pdf

Gilad Yehudai, Ohad Shamir, Gal Vardi, 2021, ICLR.

On Margin Maximization in Linear and ReLU Networks pdf

Ohad Shamir, Nathan Srebro, Gal Vardi, 2021, ArXiv.

Oracle Complexity in Nonsmooth Nonconvex Optimization pdf

Ohad Shamir, Guy Kornowski, O. Shamir, 2021, NeurIPS.

The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication

Ohad Shamir, Nathan Srebro, Blake E. Woodworth, 2021, COLT.

A Stochastic Newton Algorithm for Distributed Convex Optimization pdf

Ohad Shamir, Nathan Srebro, Blake Woodworth, 2021, ArXiv.

Convergence Results For Q-Learning With Experience Replay pdf

Ohad Shamir, Liran Szlak, O. Shamir, 2021, ArXiv.

Implicit Regularization in ReLU Networks with the Square Loss pdf

Ohad Shamir, Gal Vardi, O. Shamir, 2020, COLT.

Size and Depth Separation in Approximating Benign Functions with Neural Networks

Toniann Pitassi, Ohad Shamir, Daniel Reichman, 2021, COLT.

The Implicit Bias of Benign Overfitting

Ohad Shamir, 2022 .

The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks pdf

Gilad Yehudai, Ohad Shamir, Itay Safran, 2020, COLT.

Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems pdf

Ohad Shamir, Itay Safran, O. Shamir, 2021, NeurIPS.

Learning a Single Neuron with Bias Using Gradient Descent pdf

Gilad Yehudai, Ohad Shamir, Gal Vardi, 2021, NeurIPS.

Replay For Safety pdf

Ohad Shamir, Liran Szlak, O. Shamir, 2021, ArXiv.

The Connection Between Approximation, Depth Separation and Learnability in Neural Networks pdf

Gilad Yehudai, Ohad Shamir, Shai Shalev-Shwartz, 2021, COLT.

High-resolution microbial community reconstruction by integrating short reads from multiple 16S rRNA regions

Ohad Shamir, Noam Shental, Amnon Amir, 2013, Nucleic acids research.

Is Local SGD Better than Minibatch SGD? pdf

Ohad Shamir, Nathan Srebro, Sebastian U. Stich, 2020, ICML.