Aaron Roth

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