Nathan Kallus

Fast Best-in-Class Regret for Contextual Bandits UAI 2026 Anytime-Valid A/B Testing of Counting Processes AISTATS 2025 A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents ICML 2025 LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience EMNLP 2025 Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits ICML 2025 Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits AISTATS 2025 Variation Due to Regularization Tractably Recovers Bayesian Deep Learning Uncertainty AISTATS 2025 Contextual Linear Optimization with Bandit Feedback NeurIPS 2024 Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes NeurIPS 2024 Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data NeurIPS 2024 Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments ICML 2024 Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond JMLR 2024 Low-rank MDPs with Continuous Action Spaces AISTATS 2024 More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning ICML 2024 Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams ICML 2024 Provable Offline Preference-Based Reinforcement Learning ICLR 2024 Switching the Loss Reduces the Cost in Batch Reinforcement Learning ICML 2024 B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding ICML 2023 Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings ICML 2023 Future-Dependent Value-Based Off-Policy Evaluation in POMDPs NeurIPS 2023 Inference on Strongly Identified Functionals of Weakly Identified Functions COLT 2023 Minimax Instrumental Variable Regression and L_2 Convergence Guarantees without Identification or Closedness COLT 2023 Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR ICML 2023 Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage NeurIPS 2023 Provable Safe Reinforcement Learning with Binary Feedback AISTATS 2023 Robust and Agnostic Learning of Conditional Distributional Treatment Effects AISTATS 2023 Smooth Non-stationary Bandits ICML 2023 The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning NeurIPS 2023 Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning ICML 2022 Estimating Structural Disparities for Face Models CVPR 2022 Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects JMLR 2022 Learning Bellman Complete Representations for Offline Policy Evaluation ICML 2022 Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems NeurIPS 2022 Stateful Offline Contextual Policy Evaluation and Learning AISTATS 2022 The Implicit Delta Method NeurIPS 2022 What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment NeurIPS 2022 Control Variates for Slate Off-Policy Evaluation NeurIPS 2021 Fast Rates for the Regret of Offline Reinforcement Learning COLT 2021 Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders AISTATS 2021 Optimal Off-Policy Evaluation from Multiple Logging Policies ICML 2021 Post-Contextual-Bandit Inference NeurIPS 2021 Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning NeurIPS 2021 Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning NeurIPS 2020 DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training ICML 2020 Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation ICML 2020 Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes JMLR 2020 Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies NeurIPS 2020 Efficient Policy Learning from Surrogate-Loss Classification Reductions ICML 2020 Generalized Optimal Matching Methods for Causal Inference JMLR 2020 Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes COLT 2020 Statistically Efficient Off-Policy Policy Gradients ICML 2020 Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds NeurIPS 2019 Classifying Treatment Responders Under Causal Effect Monotonicity ICML 2019 Deep Generalized Method of Moments for Instrumental Variable Analysis NeurIPS 2019 Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding AISTATS 2019 Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning NeurIPS 2019 Policy Evaluation with Latent Confounders via Optimal Balance NeurIPS 2019 The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the XAUC Metric NeurIPS 2019 Balanced Policy Evaluation and Learning NeurIPS 2018 Causal Inference with Noisy and Missing Covariates via Matrix Factorization NeurIPS 2018 Confounding-Robust Policy Improvement NeurIPS 2018 Instrument-Armed Bandits ALT 2018 Policy Evaluation and Optimization with Continuous Treatments AISTATS 2018 Removing Hidden Confounding by Experimental Grounding NeurIPS 2018 Residual Unfairness in Fair Machine Learning from Prejudiced Data ICML 2018 A Framework for Optimal Matching for Causal Inference AISTATS 2017 Recursive Partitioning for Personalization using Observational Data ICML 2017