Nathan Kallus

发表

Fairness, Welfare, and Equity in Personalized Pricing pdf

Nathan Kallus, Angela Zhou, Nathan Kallus, 2020, FAccT.

Optimal Off-Policy Evaluation from Multiple Logging Policies pdf

Masatoshi Uehara, Yuta Saito, Nathan Kallus, 2020, ICML.

Rejoinder: New Objectives for Policy Learning pdf

Nathan Kallus, Nathan Kallus, 2020, Journal of the American Statistical Association.

Fast Rates for Contextual Linear Optimization

Nathan Kallus, Yichun Hu, Xiaojie Mao, 2020, Manag. Sci..

More Efficient Policy Learning via Optimal Retargeting pdf

Nathan Kallus, Nathan Kallus, 2019, Journal of the American Statistical Association.

Instrument-Armed Bandits pdf

Nathan Kallus, Nathan Kallus, 2017, ALT.

Learning Weighted Representations for Generalization Across Designs

Fredrik D. Johansson, D. Sontag, Uri Shalit, 2018, 1802.08598.

DTR Bandit: Learning to Make Response-Adaptive Decisions With Low Regret pdf

Nathan Kallus, Yichun Hu, Nathan Kallus, 2020, ArXiv.

Assessing algorithmic fairness with unobserved protected class using data combination

Xiaojie Mao, Nathan Kallus, Angela Zhou, 2019, FAT*.

Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

Nathan Kallus, Yichun Hu, Xiaojie Mao, 2019, COLT.

Personalized Diabetes Management Using Electronic Medical Records

Ying Daisy Zhuo, D. Bertsimas, Nathan Kallus, 2016, Diabetes Care.

Optimal a priori balance in the design of controlled experiments

Nathan Kallus, 2013, 1312.0531.

Optimal Estimation of Generalized Average Treatment Effects using Kernel Optimal Matching

Nathan Kallus, Michele Santacatterina, 2019, 1908.04748.

Kernel Optimal Orthogonality Weighting: A Balancing Approach to Estimating Effects of Continuous Treatments

Nathan Kallus, Michele Santacatterina, Nathan Kallus, 2019, 1910.11972.

Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, 2019, Oper. Res..

Efficiently Breaking the Curse of Horizon: Double Reinforcement Learning in Infinite-Horizon Processes pdf

Masatoshi Uehara, Nathan Kallus, Masatoshi Uehara, 2019, ArXiv.

Robust and Agnostic Learning of Conditional Distributional Treatment Effects

Nathan Kallus, M. Oprescu, 2022, ArXiv.

Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings

Jason D. Lee, Masatoshi Uehara, Ayush Sekhari, 2022, ICML.

What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment

Nathan Kallus, 2022, ArXiv.

Learning Bellman Complete Representations for Offline Policy Evaluation

Wen Sun, Nathan Kallus, Kaiwen Wang, 2022, ICML.

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

V. Chernozhukov, Masatoshi Uehara, Nan Jiang, 2022, ArXiv.

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data pdf

Xiaojie Mao, Nathan Kallus, Nathan Kallus, 2020, ArXiv.

2022 Debiased Inference on Identiﬁed Linear Functionals of Underidentiﬁed Nuisances via Penalized Minimax Estimation ∗

Nathan Kallus, Xiaojie Mao, 2022 .

Balanced Policy Evaluation and Learning for Right Censored Data.

M. Kosorok, M. Hudgens, Nathan Kallus, 2019, 1911.05728.

DTR Bandit: Learning to Make Response-Adaptive Decisions With Low Regret

Nathan Kallus, Yichun Hu, 2020, ArXiv.

Treatment Effect Risk: Bounds and Inference

Nathan Kallus, 2022, FAccT.

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

Zhengyuan Zhou, Nathan Kallus, Xiaojie Mao, 2022, ICML.

Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach

Masatoshi Uehara, Nathan Kallus, Xiaojie Mao, 2021, ArXiv.

The Variational Method of Moments

Nathan Kallus, Andrew Bennett, 2020, Journal of the Royal Statistical Society Series B: Statistical Methodology.

The Implicit Delta Method

Nathan Kallus, James McInerney, 2022, NeurIPS.

What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment

Nathan Kallus, 2022, NeurIPS.

Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency

Masatoshi Uehara, Nan Jiang, Wen Sun, 2021, ArXiv.

A Review of Off-Policy Evaluation in Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, C. Shi, 2022, ArXiv.

Inference on Strongly Identified Functionals of Weakly Identified Functions

W. Newey, Masatoshi Uehara, Vasilis Syrgkanis, 2022, 2208.08291.

Near-Optimal Non-Parametric Sequential Tests and Conﬁdence Sequences with Possibly Dependent Observations

Aurélien F. Bibaut, Nathan Kallus, Michael Lindon, 2023 .

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

Jason D. Lee, Masatoshi Uehara, Ayush Sekhari, 2022, NeurIPS.

Dynamic Assortment Personalization in High Dimensions

Madeleine Udell, Nathan Kallus, Madeleine Udell, 2016, Oper. Res..

Revealed Preference at Scale: Learning Personalized Preferences from Assortment Choices

Madeleine Udell, Nathan Kallus, Madeleine Udell, 2015, EC.

Learning Preferences from Assortment Choices in a Heterogeneous Population pdf

Madeleine Udell, Nathan Kallus, Madeleine Udell, 2015, ArXiv.

Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR

Wen Sun, Nathan Kallus, Kaiwen Wang, 2023, 2302.03201.

Localized Debiased Machine Learning: Efficient Estimation of Quantile Treatment Effects, Conditional Value at Risk, and Beyond pdf

Masatoshi Uehara, Xiaojie Mao, Nathan Kallus, 2019, ArXiv.

Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond

Masatoshi Uehara, Xiaojie Mao, Nathan Kallus, 2019, 1912.12945.

Data-driven robust optimization

Vishal Gupta, Dimitris Bertsimas, Nathan Kallus, 2013, Math. Program..

From data to decisions through new interfaces between optimization and statistics

Nathan Kallus, Nathan Kallus, 2015 .

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data

Nathan Kallus, Xiaojie Mao, 2020, ArXiv.

Generalized Optimal Matching Methods for Causal Inference

Nathan Kallus, Nathan Kallus, 2016, J. Mach. Learn. Res..

Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved

Madeleine Udell, Jiahao Chen, Xiaojie Mao, 2018, FAT.

The Power and Limits of Predictive Approaches to Observational-Data-Driven Optimization

Dimitris Bertsimas, Nathan Kallus, D. Bertsimas, 2016, 1605.02347.

From Predictive to Prescriptive Analytics

Dimitris Bertsimas, Nathan Kallus, D. Bertsimas, 2014, Manag. Sci..

From Predictions to Data-Driven Decisions Using Machine Learning pdf

Nathan Kallus, Nathan Kallus, 2014, ArXiv.

Stateful Offline Contextual Policy Evaluation and Learning pdf

Nathan Kallus, Angela Zhou, Nathan Kallus, 2021, AISTATS.

Comment: Entropy Learning for Dynamic Treatment Regimes pdf

Nathan Kallus, Nathan Kallus, 2020, Statistica Sinica.

Data-Pooling in Stochastic Optimization

Vishal Gupta, Nathan Kallus, Nathan Kallus, 2019, SSRN Electronic Journal.

Deep Generalized Method of Moments for Instrumental Variable Analysis

Andrew Bennett, Nathan Kallus, Tobias Schnabel, 2019, NeurIPS.

Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation

Masatoshi Uehara, Nathan Kallus, Masatoshi Uehara, 2020, ICML.

Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes

Masatoshi Uehara, Nathan Kallus, Masatoshi Uehara, 2019, J. Mach. Learn. Res..

Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding

Xiaojie Mao, Nathan Kallus, Angela Zhou, 2018, AISTATS.

Removing Hidden Confounding by Experimental Grounding

Uri Shalit, Aahlad Manas Puli, Nathan Kallus, 2018, NeurIPS.

Minimax-Optimal Policy Learning Under Unobserved Confounding

Nathan Kallus, Angela Zhou, Nathan Kallus, 2020, Manag. Sci..

Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders pdf

Ali Mousavi, Nathan Kallus, Lihong Li, 2020, AISTATS.

Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning pdf

Nathan Kallus, Angela Zhou, Nathan Kallus, 2020, NeurIPS.

Robust and Agnostic Learning of Conditional Distributional Treatment Effects

Nathan Kallus, M. Oprescu, 2022, AISTATS.

The Power of Optimization Over Randomization in Designing Experiments Involving Small Samples

Dimitris Bertsimas, Nathan Kallus, Mac Johnson, 2015, Oper. Res..

Robust sample average approximation

Vishal Gupta, Dimitris Bertsimas, Nathan Kallus, 2014, Math. Program..

Statistically Efficient Off-Policy Policy Gradients pdf

Masatoshi Uehara, Nathan Kallus, Masatoshi Uehara, 2020, ICML.

Residual Unfairness in Fair Machine Learning from Prejudiced Data

Nathan Kallus, Angela Zhou, Nathan Kallus, 2018, ICML.

Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects

Fredrik D. Johansson, D. Sontag, Uri Shalit, 2020, J. Mach. Learn. Res..

Control Variates for Slate Off-Policy Evaluation pdf

Ashok Chandrashekar, Nathan Kallus, Nikos Vlassis, 2021, NeurIPS.

Recursive Partitioning for Personalization using Observational Data

Nathan Kallus, Nathan Kallus, 2016, ICML.

Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes

Nathan Kallus, Andrew Bennett, 2021, ArXiv.

Long-term Causal Inference Under Persistent Confounding via Data Combination

G. Imbens, Nathan Kallus, Xiaojie Mao, 2022, 2202.07234.

Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confounding

Nathan Kallus, Kevin Guo, Jacob Dorn, 2021, ArXiv.

Assessing Disparate Impacts of Personalized Interventions: Identifiability and Bounds

Nathan Kallus, Angela Zhou, Nathan Kallus, 2019, ArXiv.

Optimal balancing of time-dependent confounders for marginal structural models

Nathan Kallus, Michele Santacatterina, Nathan Kallus, 2018, Journal of Causal Inference.

A Framework for Optimal Matching for Causal Inference

Nathan Kallus, Nathan Kallus, 2016, AISTATS.

B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

Uri Shalit, Nathan Kallus, A. Jesson, 2023, 2304.10577.

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric

Nathan Kallus, Angela Zhou, Nathan Kallus, 2019, NeurIPS.

Provable Offline Reinforcement Learning with Human Feedback

Jason D. Lee, Masatoshi Uehara, Wen Sun, 2023, ArXiv.

Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR

Wen Sun, Nathan Kallus, Kaiwen Wang, 2023, ICML.

The effect of patient age on discharge destination and complications after lumbar spinal fusion

Nathan Kallus, Michele Santacatterina, Brenton H. Pennicooke, 2021, Journal of clinical neuroscience.

Refined Value-Based Offline RL under Realizability and Partial Coverage

Jason D. Lee, Masatoshi Uehara, Wen Sun, 2023, ArXiv.

Estimating Structural Disparities for Face Models

Cristina Segalin, Nathan Kallus, Shervin Ardeshir, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Policy Evaluation with Latent Confounders via Optimal Balance

Nathan Kallus, Andrew Bennett, Nathan Kallus, 2019, NeurIPS.

Confounding-Robust Policy Improvement

Nathan Kallus, Angela Zhou, Nathan Kallus, 2018, NeurIPS.

Balanced Policy Evaluation and Learning

Nathan Kallus, Nathan Kallus, 2017, NeurIPS.

Learning to Personalize from Observational Data

Nathan Kallus, Nathan Kallus, 2016 .

Scheduling, revenue management, and fairness in an academic-hospital radiology division.

Dimitris Bertsimas, Nathan Kallus, Richard Baum, 2014, Academic radiology.

Inference on Strongly Identified Functionals of Weakly Identified Functions

W. Newey, Masatoshi Uehara, Vasilis Syrgkanis, 2022, COLT.

An Empirical Evaluation of the Impact of New York's Bail Reform on Crime Using Synthetic Controls

Nathan Kallus, Angela Zhou, Tiffany Bergin, 2021, Social Science Research Network.

Controlling for Unmeasured Confounding in Panel Data Using Minimal Bridge Functions: From Two-Way Fixed Effects to Factor Models

Guido Imbens, Xiaojie Mao, Nathan Kallus, 2021, 2108.03849.

Synthetic Control Analysis of the Short-Term Impact of New York State’s Bail Elimination Act on Aggregate Crime

Nathan Kallus, Angela Zhou, Tiffany Bergin, 2021, Statistics and Public Policy.

Causal Inference with Noisy and Missing Covariates via Matrix Factorization

Madeleine Udell, Xiaojie Mao, Nathan Kallus, 2018, NeurIPS.

Post-Contextual-Bandit Inference pdf

Antoine Chambaz, Nathan Kallus, Mark van der Laan, 2021, NeurIPS.

Fast Rates for the Regret of Offline Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, Yichun Hu, 2021, COLT.

Optimal weighting for estimating generalized average treatment effects

Nathan Kallus, Michele Santacatterina, 2022 .

Efficient Policy Learning from Surrogate-Loss Classification Reductions

Nathan Kallus, Andrew Bennett, Nathan Kallus, 2020, ICML.

Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies pdf

Masatoshi Uehara, Nathan Kallus, Masatoshi Uehara, 2020, NeurIPS.

Causal Inference by Minimizing the Dual Norm of Bias: Kernel Matching & Weighting Estimators for Causal Effects

Nathan Kallus, Nathan Kallus, 2016, CFA@UAI.

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

Wen Sun, Nathan Kallus, Runzhe Wu, 2023, ArXiv.

Fast Rates for the Regret of Offline Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, Yichun Hu, 2021, Annual Conference Computational Learning Theory.

Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning pdf

Antoine Chambaz, Nathan Kallus, Mark van der Laan, 2021, NeurIPS.

Policy Evaluation and Optimization with Continuous Treatments

Nathan Kallus, Angela Zhou, Nathan Kallus, 2018, AISTATS.

JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning

Wen Sun, Nathan Kallus, Immanuel Trummer, 2023, 2307.11704.

Provable Safe Reinforcement Learning with Binary Feedback

Dipendra Kumar Misra, Nathan Kallus, Andrew Bennett, 2022, AISTATS.

Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects

Fredrik D. Johansson, D. Sontag, Uri Shalit, 2020, J. Mach. Learn. Res..

DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training

Nathan Kallus, Nathan Kallus, 2018, ICML.

Stochastic Optimization Forests

Nathan Kallus, Xiaojie Mao, 2020, Manag. Sci..

B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

Uri Shalit, Nathan Kallus, A. Jesson, 2023, ICML.

Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations

Aurélien F. Bibaut, Nathan Kallus, Michael Lindon, 2022, 2212.14411.

Source Condition Double Robust Inference on Functionals of Inverse Problems

Masatoshi Uehara, Vasilis Syrgkanis, Nathan Kallus, 2023, ArXiv.

Residual Overfit Method of Exploration pdf

Nathan Kallus, James McInerney, Nathan Kallus, 2021, ArXiv.

Inventory Management in the Era of Big Data

Dimitris Bertsimas, Nathan Kallus, Amjad Hussain, 2016 .

Residual Unfairness in Fair Machine Learning from Prejudiced Data

Nathan Kallus, Angela Zhou, 2018, ICML.

More robust estimation of average treatment effects using kernel optimal matching in an observational study of spine surgical interventions

Nathan Kallus, Michele Santacatterina, Brenton Pennicooke, 2018, Statistics in medicine.

Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, 2020, Biometrika.

Large Language Models as Zero-Shot Conversational Recommenders

Bodhisattwa Prasad Majumder, H. Steck, Nathan Kallus, 2023, CIKM.

Long-term Causal Inference Under Persistent Confounding via Data Combination

G. Imbens, Nathan Kallus, Xiaojie Mao, 2022, 2202.07234.

Smooth Non-Stationary Bandits

P. Frazier, Nathan Kallus, Qian Xie, 2023, ICML.

On the Predictive Power of Web Intelligence and Social Media - The Best Way to Predict the Future Is to tweet It

Nathan Kallus, Nathan Kallus, 2014, MSM/MUSE/SenseML.

Predicting crowd behavior with big public data

Nathan Kallus, Nathan Kallus, 2014, WWW.

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

Wen Sun, Nathan Kallus, Runzhe Wu, 2023, NeurIPS.

Provable Offline Preference-Based Reinforcement Learning

Jason D. Lee, Masatoshi Uehara, Wen Sun, 2023, 2305.14816.

Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds

Nathan Kallus, Angela Zhou, 2019, Neural Information Processing Systems.

Classifying Treatment Responders Under Causal Effect Monotonicity

Nathan Kallus, Nathan Kallus, 2019, ICML.

Long-term Causal Inference Under Persistent Confounding via Data Combination

G. Imbens, Nathan Kallus, Xiaojie Mao, 2022, 2202.07234.

Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations

Aurélien F. Bibaut, Nathan Kallus, Michael Lindon, 2022, 2212.14411.

Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments

Aurélien F. Bibaut, Nathan Kallus, Allen Tran, 2023, 2311.08527.

JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning

Wen Sun, Nathan Kallus, Immanuel Trummer, 2023, ArXiv.

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

V. Chernozhukov, Masatoshi Uehara, Nan Jiang, 2022, NeurIPS.

More robust estimation of average treatment effects using kernel optimal matching in an observational study of spine surgical interventions

Nathan Kallus, Michele Santacatterina, Brenton H. Pennicooke, 2021, Statistics in medicine.

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams

Nathan Kallus, Brian Cho, Kyra Gan, 2024, ArXiv.

Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, Masatoshi Uehara, 2019, NeurIPS.

Multi-Armed Bandits with Interference

Nathan Kallus, Su Jia, Peter Frazier, 2024, 2402.01845.

Clustered Switchback Experiments: Near-Optimal Rates Under Spatiotemporal Interference

Nathan Kallus, Su Jia, Christina Lee Yu, 2023, 2312.15574.

Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects

Fredrik D. Johansson, D. Sontag, Uri Shalit, 2020, J. Mach. Learn. Res..

Near-Optimal, Near-Calibrated, Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations

Aurélien F. Bibaut, Nathan Kallus, Michael Lindon, 2022 .

An Empirical Evaluation of the Impact of New York's Bail Reform on Crime Using Synthetic Controls pdf

Nathan Kallus, Angela Zhou, Tiffany Bergin, 2021, SSRN Electronic Journal.

Hidden yet quantiﬁable: A lower bound for confounding strength using randomized trials

Roland R. Ramsahai, J. Sekhon, Nathan Kallus, 2022 .

Instrument-Armed Bandits

Nathan Kallus, 2017, ALT.

Pricing from Observational Data

Dimitris Bertsimas, Nathan Kallus, D. Bertsimas, 2016 .

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning

Nathan Kallus, Kaiwen Wang, Owen Oertell, 2024, ArXiv.

Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes

Nathan Kallus, M. Oprescu, Kaiwen Wang, 2024, 2404.00099.

Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond

Masatoshi Uehara, Nathan Kallus, Xiaojie Mao, 2019, 1912.12945.

Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness

Masatoshi Uehara, Vasilis Syrgkanis, Nathan Kallus, 2023, COLT.

Balanced Policy Evaluation and Learning for Right Censored Data.

M. Kosorok, M. Hudgens, Nathan Kallus, 2019, 1911.05728.

Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data

Nathan Kallus, M. Oprescu, 2024, arXiv.org.

Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning

Masatoshi Uehara, Nathan Kallus, 2019, Oper. Res..