Ohad Shamir

Most-cited papers

The Power of Depth for Feedforward Neural Networks
Ronen Eldan, Ohad Shamir
2015Annual Conference Computational Learning Theory813 citations
Semantic Scholar
Size-Independent Sample Complexity of Neural Networks
Noah Golowich, A. Rakhlin, Ohad Shamir
2017Annual Conference Computational Learning Theory660 citations Open access
Semantic Scholar
On the Computational Efficiency of Training Neural Networks
Roi Livni, S. Shalev-Shwartz, Ohad Shamir
2014Neural Information Processing Systems505 citations
Semantic Scholar
An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
Ohad Shamir
2015Journal of machine learning research352 citations
Semantic Scholar
Proving the Lottery Ticket Hypothesis: Pruning is All You Need
Eran Malach, Gilad Yehudai, S. Shalev-Shwartz, Ohad Shamir
2020International Conference on Machine Learning344 citations
Semantic Scholar
Is Local SGD Better than Minibatch SGD?
Blake E. Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai +4 more
2020International Conference on Machine Learning298 citations
Semantic Scholar
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
Itay Safran, Ohad Shamir
2017International Conference on Machine Learning295 citations
Semantic Scholar
Failures of Gradient-Based Deep Learning
S. Shalev-Shwartz, Ohad Shamir, Shaked Shammah
2017International Conference on Machine Learning237 citations
Semantic Scholar
Communication Complexity of Distributed Convex Learning and Optimization
Yossi Arjevani, Ohad Shamir
2015Neural Information Processing Systems228 citations
Semantic Scholar
Reconstructing Training Data from Trained Neural Networks
Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir +1 more
2022Neural Information Processing Systems201 citations Open access
Semantic Scholar
On the Power and Limitations of Random Features for Understanding Neural Networks
Gilad Yehudai, Ohad Shamir
2019Neural Information Processing Systems198 citations
Semantic Scholar
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks
Itay Safran, Ohad Shamir
2016International Conference on Machine Learning189 citations
Semantic Scholar
Multi-player bandits: a musical chairs approach
Jonathan Rosenski, Ohad Shamir, Liran Szlak
2016International Conference on Machine Learning173 citations
Semantic Scholar
Online Learning for Time Series Prediction
Oren Anava, Elad Hazan, Shie Mannor, Ohad Shamir
2013Annual Conference Computational Learning Theory168 citations
Semantic Scholar
A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate
Ohad Shamir
2014International Conference on Machine Learning166 citations
Semantic Scholar
Distributed stochastic optimization and learning
Ohad Shamir, N. Srebro
2014Allerton Conference on Communication, Control, and Computing157 citations
Semantic Scholar
Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback
N. Alon, N. Cesa-Bianchi, C. Gentile, Shie Mannor +2 more
2014SIAM journal on computing (Print)150 citations Open access
Semantic Scholar
Without-Replacement Sampling for Stochastic Gradient Methods
Ohad Shamir
2016Neural Information Processing Systems139 citations
Semantic Scholar
On the Quality of the Initial Basin in Overspecified Neural Networks
Itay Safran, Ohad Shamir
2015International Conference on Machine Learning131 citations
Semantic Scholar
Distribution-Specific Hardness of Learning Neural Networks
Ohad Shamir
2016Journal of machine learning research121 citations
Semantic Scholar
Oracle complexity of second-order methods for smooth convex optimization
Yossi Arjevani, Ohad Shamir, Ron Shiff
2017Mathematical programming120 citations Open access
Semantic Scholar
Global Non-convex Optimization with Discretized Diffusions
Murat A. Erdogdu, L. Mackey, Ohad Shamir
2018Neural Information Processing Systems109 citations
Semantic Scholar
How Good is SGD with Random Shuffling?
Itay Safran, Ohad Shamir
2019Annual Conference Computational Learning Theory105 citations
Semantic Scholar
On-demand, Spot, or Both: Dynamic Resource Allocation for Executing Batch Jobs in the Cloud
I. Menache, Ohad Shamir, Navendu Jain
2014International Conference on Automation and Computing104 citations
Semantic Scholar
Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity
Ohad Shamir
2015International Conference on Machine Learning99 citations
Semantic Scholar
Convergence of Stochastic Gradient Descent for PCA
Ohad Shamir
2015International Conference on Machine Learning92 citations
Semantic Scholar
Probabilistic Label Trees for Efficient Large Scale Image Classification
Baoyuan Liu, Fereshteh Sadeghi, Marshall F. Tappen, Ohad Shamir +1 more
20132013 IEEE Conference on Computer Vision and Pattern Recognition88 citations Open access
Semantic Scholar
Learning a Single Neuron with Gradient Methods
Gilad Yehudai, Ohad Shamir
2020Annual Conference Computational Learning Theory77 citations
Semantic Scholar
A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates
Yossi Arjevani, Ohad Shamir, N. Srebro
2018International Conference on Algorithmic Learning Theory77 citations
Semantic Scholar
Oracle Complexity in Nonsmooth Nonconvex Optimization
Guy Kornowski, Ohad Shamir
2021Neural Information Processing Systems76 citations
Semantic Scholar
The Complexity of Finding Stationary Points with Stochastic Gradient Descent
Yoel Drori, Ohad Shamir
2019International Conference on Machine Learning75 citations
Semantic Scholar
Implicit Regularization Towards Rank Minimization in ReLU Networks
N. Timor, Gal Vardi, Ohad Shamir
2022International Conference on Algorithmic Learning Theory70 citations
Semantic Scholar
The Complexity of Making the Gradient Small in Stochastic Convex Optimization
Dylan J. Foster, Ayush Sekhari, Ohad Shamir, N. Srebro +2 more
2019Annual Conference Computational Learning Theory70 citations
Semantic Scholar
Implicit Regularization in ReLU Networks with the Square Loss
Gal Vardi, Ohad Shamir
2020Annual Conference Computational Learning Theory57 citations
Semantic Scholar
Are ResNets Provably Better than Linear Predictors?
Ohad Shamir
2018Neural Information Processing Systems56 citations
Semantic Scholar
The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication
Blake E. Woodworth, Brian Bullins, Ohad Shamir, N. Srebro
2021Annual Conference Computational Learning Theory55 citations Open access
Semantic Scholar
High-resolution microbial community reconstruction by integrating short reads from multiple 16S rRNA regions
Amnon Amir, A. Zeisel, O. Zuk, Michael Elgart +5 more
2013Nucleic Acids Research55 citations Open access
Semantic Scholar
The Implicit Bias of Benign Overfitting
Ohad Shamir
2022Annual Conference Computational Learning Theory54 citations
Semantic Scholar
Exponential Convergence Time of Gradient Descent for One-Dimensional Deep Linear Neural Networks
Ohad Shamir
2018Annual Conference Computational Learning Theory54 citations
Semantic Scholar
An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization
Guy Kornowski, Ohad Shamir
2023Journal of machine learning research51 citations Open access
Semantic Scholar
On the Optimal Memorization Power of ReLU Neural Networks
Gal Vardi, Gilad Yehudai, Ohad Shamir
2021International Conference on Learning Representations49 citations
Semantic Scholar
Deterministic Nonsmooth Nonconvex Optimization
Michael I. Jordan, Guy Kornowski, Tianyi Lin, Ohad Shamir +1 more
2023Annual Conference Computational Learning Theory48 citations Open access
Semantic Scholar
The sample complexity of learning linear predictors with the squared loss
Ohad Shamir
2014Journal of machine learning research47 citations
Semantic Scholar
The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks
Itay Safran, Gilad Yehudai, Ohad Shamir
2020Annual Conference Computational Learning Theory46 citations
Semantic Scholar
Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
D. Garber, Ohad Shamir, N. Srebro
2017International Conference on Machine Learning45 citations
Semantic Scholar
Matrix completion with the trace norm: learning, bounding, and transducing
Ohad Shamir, S. Shalev-Shwartz
2014Journal of machine learning research45 citations
Semantic Scholar
Depth Separations in Neural Networks: What is Actually Being Separated?
Itay Safran, Ronen Eldan, Ohad Shamir
2019Constructive approximation43 citations Open access
Semantic Scholar
Detecting Correlations with Little Memory and Communication
Y. Dagan, Ohad Shamir
2018Annual Conference Computational Learning Theory43 citations
Semantic Scholar
On the Iteration Complexity of Oblivious First-Order Optimization Algorithms
Yossi Arjevani, Ohad Shamir
2016International Conference on Machine Learning43 citations
Semantic Scholar
On Lower and Upper Bounds in Smooth and Strongly Convex Optimization
Yossi Arjevani, S. Shalev-Shwartz, Ohad Shamir
2016Journal of machine learning research43 citations
Semantic Scholar