Nati Srebro

Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy NeurIPS 2023 Most Neural Networks Are Almost Learnable NeurIPS 2023 The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks NeurIPS 2023 Uniform Convergence with Square-Root Lipschitz Loss NeurIPS 2023 When is Agnostic Reinforcement Learning Statistically Tractable? NeurIPS 2023 Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization NeurIPS 2022 A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models NeurIPS 2022 Exponential Family Model-Based Reinforcement Learning via Score Matching NeurIPS 2022 On Margin Maximization in Linear and ReLU Networks NeurIPS 2022 Pessimism for Offline Linear Contextual Bandits using ℓ_p Confidence Sets NeurIPS 2022 The Sample Complexity of One-Hidden-Layer Neural Networks NeurIPS 2022 Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization NeurIPS 2022 Towards Optimal Communication Complexity in Distributed Non-Convex Optimization NeurIPS 2022 Understanding the Eluder Dimension NeurIPS 2022 Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NeurIPS 2020 Minibatch vs Local SGD for Heterogeneous Distributed Learning NeurIPS 2020 On Uniform Convergence and Low-Norm Interpolation Learning NeurIPS 2020 Reducing Adversarially Robust Learning to Non-Robust PAC Learning NeurIPS 2020 Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization NeurIPS 2018 Implicit Bias of Gradient Descent on Linear Convolutional Networks NeurIPS 2018 On preserving non-discrimination when combining expert advice NeurIPS 2018 The Everlasting Database: Statistical Validity at a Fair Price NeurIPS 2018 Exploring Generalization in Deep Learning NeurIPS 2017 Implicit Regularization in Matrix Factorization NeurIPS 2017 Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data AISTATS 2017 Stochastic Approximation for Canonical Correlation Analysis NeurIPS 2017 The Marginal Value of Adaptive Gradient Methods in Machine Learning NeurIPS 2017 Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis NeurIPS 2016 Equality of Opportunity in Supervised Learning NeurIPS 2016 Global Optimality of Local Search for Low Rank Matrix Recovery NeurIPS 2016 Normalized Spectral Map Synchronization NeurIPS 2016 Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations NeurIPS 2016 Tight Complexity Bounds for Optimizing Composite Objectives NeurIPS 2016 Path-SGD: Path-Normalized Optimization in Deep Neural Networks NeurIPS 2015 Communication-Efficient Distributed Optimization using an Approximate Newton-type Method ICML 2014 Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm NeurIPS 2014 Auditing: Active Learning with Outcome-Dependent Query Costs NeurIPS 2013 Learning Optimally Sparse Support Vector Machines ICML 2013 Mini-Batch Primal and Dual Methods for SVMs ICML 2013 Stochastic Optimization of PCA with Capped MSG NeurIPS 2013 The Power of Asymmetry in Binary Hashing NeurIPS 2013 Beating SGD: Learning SVMs in Sublinear Time NeurIPS 2011 Better Mini-Batch Algorithms via Accelerated Gradient Methods NeurIPS 2011 Learning with the weighted trace-norm under arbitrary sampling distributions NeurIPS 2011 On the Universality of Online Mirror Descent NeurIPS 2011