Shai Shalev-shwartz

Jamba: Hybrid Transformer-Mamba Language Models ICLR 2025 Knowledge Distillation: Bad Models Can Be Good Role Models NeurIPS 2022 When Hardness of Approximation Meets Hardness of Learning JMLR 2022 Computational Separation Between Convolutional and Fully-Connected Networks ICLR 2021 Distribution Free Learning with Local Queries ALT 2020 SenseBERT: Driving Some Sense into BERT ACL 2020 The Implications of Local Correlation on Learning Some Deep Functions NeurIPS 2020 The Implicit Bias of Depth: How Incremental Learning Drives Generalization ICLR 2020 Is Deeper Better only when Shallow is Good? NeurIPS 2019 Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization JMLR 2018 SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data ICLR 2018 Decoupling "when to update" from "how to update" NeurIPS 2017 Effective Semisupervised Learning on Manifolds COLT 2017 Failures of Gradient-Based Deep Learning ICML 2017 Fast Rates for Empirical Risk Minimization of Strict Saddle Problems COLT 2017 Complexity Theoretic Limitations on Learning DNF’s COLT 2016 Learning a Metric Embedding for Face Recognition using the Multibatch Method NeurIPS 2016 Minimizing the Maximal Loss: How and Why ICML 2016 On Graduated Optimization for Stochastic Non-Convex Problems ICML 2016 On Lower and Upper Bounds in Smooth and Strongly Convex Optimization JMLR 2016 SDCA without Duality, Regularization, and Individual Convexity ICML 2016 Solving Ridge Regression using Sketched Preconditioned SVRG ICML 2016 Subspace Learning with Partial Information JMLR 2016 Beyond Convexity: Stochastic Quasi-Convex Optimization NeurIPS 2015 Learning Sparse Low-Threshold Linear Classifiers JMLR 2015 Multiclass Learnability and the ERM Principle JMLR 2015 Strongly Adaptive Online Learning ICML 2015 Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization ICML 2014 K-means recovers ICA filters when independent components are sparse ICML 2014 Matrix Completion with the Trace Norm: Learning, Bounding, and Transducing JMLR 2014 On the Computational Efficiency of Training Neural Networks NeurIPS 2014 Optimal learners for multiclass problems COLT 2014 The Complexity of Learning Halfspaces using Generalized Linear Methods COLT 2014 Accelerated Mini-Batch Stochastic Dual Coordinate Ascent NeurIPS 2013 Efficient Active Learning of Halfspaces: an Aggressive Approach ICML 2013 Efficient Active Learning of Halfspaces: An Aggressive Approach JMLR 2013 Learning Optimally Sparse Support Vector Machines ICML 2013 More data speeds up training time in learning halfspaces over sparse vectors NeurIPS 2013 Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization JMLR 2013 Vanishing Component Analysis ICML 2013 Near-Optimal Algorithms for Online Matrix Prediction COLT 2012 Regularization Techniques for Learning with Matrices JMLR 2012 Using More Data to Speed-up Training Time AISTATS 2012 Collaborative Filtering with the Trace Norm: Learning, Bounding, and Transducing COLT 2011 Efficient Learning with Partially Observed Attributes JMLR 2011 Multiclass Learnability and the ERM principle COLT 2011 ShareBoost: Efficient multiclass learning with feature sharing NeurIPS 2011 Stochastic Methods for -regularized Loss Minimization JMLR 2011 Learnability, Stability and Uniform Convergence JMLR 2010 Fast Rates for Regularized Objectives NeurIPS 2008 Mind the Duality Gap: Logarithmic regret algorithms for online optimization NeurIPS 2008 Online Learning of Complex Prediction Problems Using Simultaneous Projections JMLR 2008 Ranking Categorical Features Using Generalization Properties JMLR 2008 Convex Repeated Games and Fenchel Duality NeurIPS 2006 Efficient Learning of Label Ranking by Soft Projections onto Polyhedra JMLR 2006 Online Classification for Complex Problems Using Simultaneous Projections NeurIPS 2006 Online Passive-Aggressive Algorithms JMLR 2006 Smooth ε-Insensitive Regression by Loss Symmetrization JMLR 2005 A Unified Algorithmic Approach for Efficient Online Label Ranking AISTATS 1999