Aaron Roth

Model Agreement via Anchoring COLT 2026 Omniprediction with Long-Term Constraints COLT 2026 Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation ICLR 2025 Conformal Language Model Reasoning with Coherent Factuality ICLR 2025 Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents ICML 2025 High-Dimensional Prediction for Sequential Decision Making ICML 2025 Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces ICML 2025 Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Losses COLT 2025 Stronger Neyman Regret Guarantees for Adaptive Experimental Design ICML 2025 The Relationship Between No-Regret Learning and Online Conformal Prediction ICML 2025 Conference on Learning Theory 2024: Preface COLT 2024 Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks ICML 2024 Membership Inference Attacks on Diffusion Models via Quantile Regression ICML 2024 Multicalibration for Confidence Scoring in LLMs ICML 2024 Oracle Efficient Algorithms for Groupwise Regret ICLR 2024 Oracle-Efficient Reinforcement Learning for Max Value Ensembles NeurIPS 2024 Order of Magnitude Speedups for LLM Membership Inference EMNLP 2024 Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable NeurIPS 2024 Batch Multivalid Conformal Prediction ICLR 2023 Individually Fair Learning with One-Sided Feedback ICML 2023 Multicalibration as Boosting for Regression ICML 2023 Scalable Membership Inference Attacks via Quantile Regression NeurIPS 2023 The Statistical Scope of Multicalibration ICML 2023 Mixed Differential Privacy in Computer Vision CVPR 2022 Online Minimax Multiobjective Optimization: Multicalibeating and Other Applications NeurIPS 2022 Practical Adversarial Multivalid Conformal Prediction NeurIPS 2022 Private Synthetic Data for Multitask Learning and Marginal Queries NeurIPS 2022 Adaptive Machine Unlearning NeurIPS 2021 Descent-to-Delete: Gradient-Based Methods for Machine Unlearning ALT 2021 Differentially Private Query Release Through Adaptive Projection ICML 2021 Moment Multicalibration for Uncertainty Estimation COLT 2021 Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis AISTATS 2020 Oracle Efficient Private Non-Convex Optimization ICML 2020 Average Individual Fairness: Algorithms, Generalization and Experiments NeurIPS 2019 Differentially Private Fair Learning ICML 2019 Equal Opportunity in Online Classification with Partial Feedback NeurIPS 2019 A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem NeurIPS 2018 Local Differential Privacy for Evolving Data NeurIPS 2018 Mitigating Bias in Adaptive Data Gathering via Differential Privacy ICML 2018 Online Learning with an Unknown Fairness Metric NeurIPS 2018 Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness ICML 2018 Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM NeurIPS 2017 Fairness in Reinforcement Learning ICML 2017 Meritocratic Fairness for Cross-Population Selection ICML 2017 Adaptive Learning with Robust Generalization Guarantees COLT 2016 Fairness in Learning: Classic and Contextual Bandits NeurIPS 2016 Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs NeurIPS 2016 Privacy Odometers and Filters: Pay-as-you-Go Composition NeurIPS 2016 Tight Policy Regret Bounds for Improving and Decaying Bandits IJCAI 2016 Generalization in Adaptive Data Analysis and Holdout Reuse NeurIPS 2015 Dual Query: Practical Private Query Release for High Dimensional Data ICML 2014