Avrim Blum

Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem UAI 2026 A Theoretical Model for Grit in Pursuing Ambitious Ends AAAI 2026 Regularized Robustly Reliable Learners ALT 2026 A Model for Combinatorial Dictionary Learning and Inference ALT 2025 Distributional Adversarial Loss AISTATS 2025 Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem ALT 2025 PAC Learning with Improvements ICML 2025 Proofs as Explanations: Short Certificates for Reliable Predictions COLT 2025 Agnostic Multi-Robust Learning using ERM AISTATS 2024 Dueling Optimization with a Monotone Adversary ALT 2024 On the Vulnerability of Fairness Constrained Learning to Malicious Noise AISTATS 2024 An Analysis of Robustness of Non-Lipschitz Networks JMLR 2023 Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback NeurIPS 2023 Strategic Classification under Unknown Personalized Manipulation NeurIPS 2023 A Theory of PAC Learnability under Transformation Invariances NeurIPS 2022 Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness NeurIPS 2022 Robustly-reliable learners under poisoning attacks COLT 2022 Communication-Aware Collaborative Learning AAAI 2021 Excess Capacity and Backdoor Poisoning NeurIPS 2021 Learning Complexity of Simulated Annealing AISTATS 2021 One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning ICML 2021 Robust learning under clean-label attack COLT 2021 Active Local Learning COLT 2020 Online Learning with Primary and Secondary Losses NeurIPS 2020 Random Smoothing Might be Unable to Certify ℓ_∞ Robustness for High-Dimensional Images JMLR 2020 Active Tolerant Testing COLT 2018 On preserving non-discrimination when combining expert advice NeurIPS 2018 Collaborative PAC Learning NeurIPS 2017 Efficient Co-Training of Linear Separators under Weak Dependence COLT 2017 Efficient PAC Learning from the Crowd COLT 2017 Lifelong Learning in Costly Feature Spaces ALT 2017 Efficient Representations for Lifelong Learning and Autoencoding COLT 2015 The Ladder: A Reliable Leaderboard for Machine Learning Competitions ICML 2015 Active Learning and Best-Response Dynamics NeurIPS 2014 Learning Mixtures of Ranking Models NeurIPS 2014 Learning Optimal Commitment to Overcome Insecurity NeurIPS 2014 Exploiting Ontology Structures and Unlabeled Data for Learning ICML 2013 Distributed Learning, Communication Complexity and Privacy COLT 2012 Trading off Mistakes and Don't-Know Predictions NeurIPS 2010 Tracking Dynamic Sources of Malicious Activity at Internet Scale NeurIPS 2009 From External to Internal Regret JMLR 2007 Preference Elicitation and Query Learning JMLR 2004