Roi Livni

CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale CVPR 2026 Learning from Equivalence Queries, Revisited COLT 2026 Margin in Abstract Spaces COLT 2026 Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization ICML 2025 Credit Attribution and Stable Compression NeurIPS 2024 Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing ICML 2024 The sample complexity of ERMs in stochastic convex optimization AISTATS 2024 The Sample Complexity of Gradient Descent in Stochastic Convex Optimization NeurIPS 2024 Information Theoretic Lower Bounds for Information Theoretic Upper Bounds NeurIPS 2023 Benign Underfitting of Stochastic Gradient Descent NeurIPS 2022 Better Best of Both Worlds Bounds for Bandits with Switching Costs NeurIPS 2022 Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization NeurIPS 2022 Littlestone Classes are Privately Online Learnable NeurIPS 2021 Never Go Full Batch (in Stochastic Convex Optimization) NeurIPS 2021 Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games COLT 2021 SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021 A Limitation of the PAC-Bayes Framework NeurIPS 2020 Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study NeurIPS 2020 Prediction with Corrupted Expert Advice NeurIPS 2020 Synthetic Data Generators -- Sequential and Private NeurIPS 2020 Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning ALT 2019 Graph-based Discriminators: Sample Complexity and Expressiveness NeurIPS 2019 On Communication Complexity of Classification Problems COLT 2019 Affine-Invariant Online Optimization and the Low-rank Experts Problem NeurIPS 2017 Bandits with Movement Costs and Adaptive Pricing COLT 2017 Effective Semisupervised Learning on Manifolds COLT 2017 Learning Infinite Layer Networks Without the Kernel Trick ICML 2017 Multi-Armed Bandits with Metric Movement Costs NeurIPS 2017 Improper Deep Kernels AISTATS 2016 Online Learning with Low Rank Experts COLT 2016 Online Pricing with Strategic and Patient Buyers NeurIPS 2016 Classification with Low Rank and Missing Data ICML 2015 On the Computational Efficiency of Training Neural Networks NeurIPS 2014 Honest Compressions and Their Application to Compression Schemes COLT 2013 Vanishing Component Analysis ICML 2013 A Simple Geometric Interpretation of SVM using Stochastic Adversaries AISTATS 2012