S. Shalev-Shwartz

Most-cited papers

Understanding Machine Learning - From Theory to Algorithms
S. Shalev-Shwartz, Shai Ben-David
20144,178 citations
Semantic Scholar
Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
S. Shalev-Shwartz, Shaked Shammah, A. Shashua
2016arXiv.org954 citations
Semantic Scholar
On a Formal Model of Safe and Scalable Self-driving Cars
S. Shalev-Shwartz, Shaked Shammah, A. Shashua
2017arXiv.org904 citations
Semantic Scholar
Decoupling "when to update" from "how to update"
Eran Malach, S. Shalev-Shwartz
2017Neural Information Processing Systems671 citations
Semantic Scholar
Stochastic Gradient Descent
S. Shalev-Shwartz, Shai Ben-David
2014Machine Learning with Neural Networks613 citations
Semantic Scholar
Jamba: A Hybrid Transformer-Mamba Language Model
Opher Lieber, Barak Lenz, Hofit Bata, Gal Cohen +18 more
2024arXiv.org536 citations
Semantic Scholar
On the Computational Efficiency of Training Neural Networks
Roi Livni, S. Shalev-Shwartz, Ohad Shamir
2014Neural Information Processing Systems505 citations
Semantic Scholar
Managing extreme AI risks amid rapid progress
Y. Bengio, G. Hinton, A. Yao, D. Song +21 more
2023Science485 citations Open access
Semantic Scholar
Understanding Machine Learning: From Theory to Algorithms
S. Shalev-Shwartz, S. Ben-David
2014457 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
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Alon Brutzkus, A. Globerson, Eran Malach, S. Shalev-Shwartz
2017International Conference on Learning Representations288 citations
Semantic Scholar
Failures of Gradient-Based Deep Learning
S. Shalev-Shwartz, Ohad Shamir, Shaked Shammah
2017International Conference on Machine Learning237 citations
Semantic Scholar
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
Ehud Karpas, Omri Abend, Yonatan Belinkov, Barak Lenz +13 more
2022arXiv.org230 citations Open access
Semantic Scholar
Strongly Adaptive Online Learning
Amit Daniely, Alon Gonen, S. Shalev-Shwartz
2015International Conference on Machine Learning215 citations
Semantic Scholar
Beyond Convexity: Stochastic Quasi-Convex Optimization
Elad Hazan, K. Levy, S. Shalev-Shwartz
2015Neural Information Processing Systems212 citations
Semantic Scholar
SenseBERT: Driving Some Sense into BERT
Yoav Levine, Barak Lenz, O. Dagan, Ori Ram +5 more
2019Annual Meeting of the Association for Computational Linguistics209 citations Open access
Semantic Scholar
Discriminative Active Learning
Daniel Gissin, S. Shalev-Shwartz
2019arXiv.org200 citations
Semantic Scholar
Accelerated Mini-Batch Stochastic Dual Coordinate Ascent
S. Shalev-Shwartz, Tong Zhang
2013Neural Information Processing Systems154 citations
Semantic Scholar
On Graduated Optimization for Stochastic Non-Convex Problems
Elad Hazan, K. Levy, S. Shalev-Shwartz
2015International Conference on Machine Learning132 citations
Semantic Scholar
Complexity Theoretic Limitations on Learning DNF's
Amit Daniely, S. Shalev-Shwartz
2014Annual Conference Computational Learning Theory124 citations
Semantic Scholar
Optimal learners for multiclass problems
Amit Daniely, S. Shalev-Shwartz
2014Annual Conference Computational Learning Theory124 citations
Semantic Scholar
SDCA without Duality, Regularization, and Individual Convexity
S. Shalev-Shwartz
2016International Conference on Machine Learning109 citations
Semantic Scholar
The Implicit Bias of Depth: How Incremental Learning Drives Generalization
Daniel Gissin, S. Shalev-Shwartz, Amit Daniely
2019International Conference on Learning Representations96 citations
Semantic Scholar
Minimizing the Maximal Loss: How and Why
S. Shalev-Shwartz, Y. Wexler
2016International Conference on Machine Learning95 citations
Semantic Scholar
Managing AI Risks in an Era of Rapid Progress
Y. Bengio, G. Hinton, A. Yao, D. Song +20 more
2023arXiv.org88 citations
Semantic Scholar
Long-term Planning by Short-term Prediction
S. Shalev-Shwartz, Nir Ben-Zrihem, Aviad Cohen, A. Shashua
2016arXiv.org62 citations
Semantic Scholar
On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training
S. Shalev-Shwartz, A. Shashua
2016arXiv.org58 citations
Semantic Scholar
Is Deeper Better only when Shallow is Good?
Eran Malach, S. Shalev-Shwartz
2019Neural Information Processing Systems54 citations
Semantic Scholar
Standing on the Shoulders of Giant Frozen Language Models
Yoav Levine, Itay Dalmedigos, Ori Ram, Yoel Zeldes +9 more
2022arXiv.org53 citations Open access
Semantic Scholar
Learning a Metric Embedding for Face Recognition using the Multibatch Method
Oren Tadmor, Y. Wexler, Tal Rosenwein, S. Shalev-Shwartz +1 more
2016Neural Information Processing Systems53 citations
Semantic Scholar
Vanishing Component Analysis
Roi Livni, D. Lehavi, Sagi Schein, Hila Nachlieli +2 more
2013International Conference on Machine Learning52 citations
Semantic Scholar
Solving Ridge Regression using Sketched Preconditioned SVRG
Alon Gonen, F. Orabona, S. Shalev-Shwartz
2016International Conference on Machine Learning50 citations
Semantic Scholar
SDCA without Duality
S. Shalev-Shwartz
2015arXiv.org48 citations
Semantic Scholar
Learning Optimally Sparse Support Vector Machines
Andrew Cotter, S. Shalev-Shwartz, N. Srebro
2013International Conference on Machine Learning47 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
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
A Provably Correct Algorithm for Deep Learning that Actually Works
Eran Malach, S. Shalev-Shwartz
2018arXiv.org41 citations
Semantic Scholar
Subspace Learning with Partial Information
Alon Gonen, Dan Rosenbaum, Yonina C. Eldar, S. Shalev-Shwartz
2014Journal of machine learning research38 citations
Semantic Scholar
An Algorithm for Training Polynomial Networks
Roi Livni, S. Shalev-Shwartz, Ohad Shamir
201335 citations
Semantic Scholar
Computational Separation Between Convolutional and Fully-Connected Networks
Eran Malach, S. Shalev-Shwartz
2020International Conference on Learning Representations33 citations
Semantic Scholar
Decoupling Gating from Linearity
Jonathan Fiat, Eran Malach, S. Shalev-Shwartz
2018arXiv.org32 citations
Semantic Scholar
Fast Rates for Empirical Risk Minimization of Strict Saddle Problems
Alon Gonen, S. Shalev-Shwartz
2017Annual Conference Computational Learning Theory31 citations
Semantic Scholar
Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization
Alon Gonen, S. Shalev-Shwartz
2016Journal of machine learning research28 citations
Semantic Scholar
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks
Eran Malach, Gilad Yehudai, S. Shalev-Shwartz, Ohad Shamir
2021Annual Conference Computational Learning Theory25 citations
Semantic Scholar
On Lower and Upper Bounds for Smooth and Strongly Convex Optimization Problems
Yossi Arjevani, S. Shalev-Shwartz, Ohad Shamir
2015arXiv.org25 citations
Semantic Scholar
A Provably Efficient Algorithm for Training Deep Networks
Roi Livni, S. Shalev-Shwartz, Ohad Shamir
2013arXiv.org24 citations
Semantic Scholar
Understanding Machine Learning: Preface
S. Shalev-Shwartz, Shai Ben-David
201422 citations
Semantic Scholar
Knowledge Distillation: Bad Models Can Be Good Role Models
Gal Kaplun, Eran Malach, Preetum Nakkiran, S. Shalev-Shwartz
2022Neural Information Processing Systems19 citations Open access
Semantic Scholar
Failures of Deep Learning
S. Shalev-Shwartz, Ohad Shamir, Shaked Shammah
2017arXiv.org19 citations
Semantic Scholar
Faster SGD Using Sketched Conditioning
Alon Gonen, S. Shalev-Shwartz
2015arXiv.org18 citations
Semantic Scholar