Nathan Kallus

According to our database, Nathan Kallus authored at least 120 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Adjusting regression models for conditional uncertainty calibration.

Ruijiang Gao, Mingzhang Yin, James McInerney, Nathan Kallus

Mach. Learn., December, 2024

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

Nathan Kallus, Xiaojie Mao, Masatoshi Uehara

J. Mach. Learn. Res., 2024

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

Andrew Bennett, Nathan Kallus

Oper. Res., 2024

Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits.

Brian Cho, Dominik Meier, Kyra Gan, Nathan Kallus

CoRR, 2024

The Central Role of the Loss Function in Reinforcement Learning.

Kaiwen Wang, Nathan Kallus, Wen Sun

CoRR, 2024

CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies.

Brian Cho, Ana-Roxana Pop, Kyra Gan, Sam Corbett-Davies, Israel Nir, Ariel Evnine, Nathan Kallus

CoRR, 2024

Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data.

Miruna Oprescu, Nathan Kallus

CoRR, 2024

Contextual Linear Optimization with Bandit Feedback.

Yichun Hu, Nathan Kallus, Xiaojie Mao, Yanchen Wu

CoRR, 2024

Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation.

Zhankui He, Zhouhang Xie, Harald Steck, Dawen Liang, Rahul Jha, Nathan Kallus, Julian J. McAuley

CoRR, 2024

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

Andrew Bennett, Nathan Kallus, Miruna Oprescu, Wen Sun, Kaiwen Wang

CoRR, 2024

Hessian-Free Laplace in Bayesian Deep Learning.

James McInerney, Nathan Kallus

CoRR, 2024

Risk-Sensitive RL with Optimized Certainty Equivalents via Reduction to Standard RL.

Kaiwen Wang, Dawen Liang, Nathan Kallus, Wen Sun

CoRR, 2024

Applied Causal Inference Powered by ML and AI.

Victor Chernozhukov, Christian Hansen, Nathan Kallus, Martin Spindler, Vasilis Syrgkanis

CoRR, 2024

Multi-Armed Bandits with Interference.

Su Jia, Peter I. Frazier, Nathan Kallus

CoRR, 2024

Is Cosine-Similarity of Embeddings Really About Similarity?

Harald Steck, Chaitanya Ekanadham, Nathan Kallus

Proceedings of the Companion Proceedings of the ACM on Web Conference 2024, 2024

Off-Policy Evaluation for Large Action Spaces via Policy Convolution.

Noveen Sachdeva, Lequn Wang, Dawen Liang, Nathan Kallus, Julian J. McAuley

Proceedings of the ACM on Web Conference 2024, 2024

JoinGym: An Efficient Join Order Selection Environment.

Junxiong Wang, Kaiwen Wang, Yueying Li, Nathan Kallus, Immanuel Trummer, Wen Sun

RLJ, 2024

Neighborhood-Based Collaborative Filtering for Conversational Recommendation.

Zhouhang Xie, Junda Wu, Hyunsik Jeon, Zhankui He, Harald Steck, Rahul Jha, Dawen Liang, Nathan Kallus, Julian J. McAuley

Proceedings of the 18th ACM Conference on Recommender Systems, 2024

Learning the Covariance of Treatment Effects Across Many Weak Experiments.

Aurélien Bibaut, Winston Chou, Simon Ejdemyr, Nathan Kallus

Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

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

Kaiwen Wang, Owen Oertell, Alekh Agarwal, Nathan Kallus, Wen Sun

Proceedings of the Forty-first International Conference on Machine Learning, 2024

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

Allen Tran, Aurélien Bibaut, Nathan Kallus

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Switching the Loss Reduces the Cost in Batch Reinforcement Learning.

Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesvári

Proceedings of the Forty-first International Conference on Machine Learning, 2024

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

Brian Cho, Kyra Gan, Nathan Kallus

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provable Offline Preference-Based Reinforcement Learning.

Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Low-rank MDPs with Continuous Action Spaces.

Miruna Oprescu, Andrew Bennett, Nathan Kallus

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Treatment Effect Risk: Bounds and Inference.

Nathan Kallus

Manag. Sci., August, 2023

Stochastic Optimization Forests.

Nathan Kallus, Xiaojie Mao

Manag. Sci., April, 2023

The Power and Limits of Predictive Approaches to Observational Data-Driven Optimization: The Case of Pricing.

Dimitris Bertsimas, Nathan Kallus

INFORMS J. Optim., January, 2023

Faster Rates for Switchback Experiments.

Su Jia, Sohom Bhattacharya, Nathan Kallus, Christina Lee Yu

CoRR, 2023

Source Condition Double Robust Inference on Functionals of Inverse Problems.

Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

CoRR, 2023

JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning.

Kaiwen Wang, Junxiong Wang, Yueying Li, Nathan Kallus, Immanuel Trummer, Wen Sun

CoRR, 2023

Provable Offline Reinforcement Learning with Human Feedback.

Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun

CoRR, 2023

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

Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

CoRR, 2023

Refined Value-Based Offline RL under Realizability and Partial Coverage.

Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun

CoRR, 2023

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

Kaiwen Wang, Kevin Zhou, Runzhe Wu, Nathan Kallus, Wen Sun

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage.

Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Masatoshi Uehara, Haruka Kiyohara, Andrew Bennett, Victor Chernozhukov, Nan Jiang, Nathan Kallus, Chengchun Shi, Wen Sun

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Kaiwen Wang, Nathan Kallus, Wen Sun

Proceedings of the International Conference on Machine Learning, 2023

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

Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun

Proceedings of the International Conference on Machine Learning, 2023

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

Miruna Oprescu, Jacob Dorn, Marah Ghoummaid, Andrew Jesson, Nathan Kallus, Uri Shalit

Proceedings of the International Conference on Machine Learning, 2023

Smooth Non-stationary Bandits.

Su Jia, Qian Xie, Nathan Kallus, Peter I. Frazier

Proceedings of the International Conference on Machine Learning, 2023

Minimax Instrumental Variable Regression and L₂ Convergence Guarantees without Identification or Closedness.

Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Inference on Strongly Identified Functionals of Weakly Identified Functions.

Andrew Bennett, Nathan Kallus, Xiaojie Mao, Whitney Newey, Vasilis Syrgkanis, Masatoshi Uehara

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Large Language Models as Zero-Shot Conversational Recommenders.

Zhankui He, Zhouhang Xie, Rahul Jha, Harald Steck, Dawen Liang, Yesu Feng, Bodhisattwa Prasad Majumder, Nathan Kallus, Julian J. McAuley

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

Robust and Agnostic Learning of Conditional Distributional Treatment Effects.

Nathan Kallus, Miruna Oprescu

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Provable Safe Reinforcement Learning with Binary Feedback.

Andrew Bennett, Dipendra Misra, Nathan Kallus

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

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

Nathan Kallus, Masatoshi Uehara

Oper. Res., November, 2022

Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes.

Yichun Hu, Nathan Kallus, Xiaojie Mao

Oper. Res., November, 2022

Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination.

Nathan Kallus, Xiaojie Mao, Angela Zhou

Manag. Sci., 2022

Fast Rates for Contextual Linear Optimization.

Yichun Hu, Nathan Kallus, Xiaojie Mao

Manag. Sci., 2022

Data Pooling in Stochastic Optimization.

Vishal Gupta, Nathan Kallus

Manag. Sci., 2022

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

Fredrik D. Johansson, Uri Shalit, Nathan Kallus, David A. Sontag

J. Mach. Learn. Res., 2022

A Review of Off-Policy Evaluation in Reinforcement Learning.

Masatoshi Uehara, Chengchun Shi, Nathan Kallus

CoRR, 2022

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems.

Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The Implicit Delta Method.

Nathan Kallus, James McInerney

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Nathan Kallus

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning.

Nathan Kallus, Xiaojie Mao, Kaiwen Wang, Zhengyuan Zhou

Proceedings of the International Conference on Machine Learning, 2022

Learning Bellman Complete Representations for Offline Policy Evaluation.

Jonathan D. Chang, Kaiwen Wang, Nathan Kallus, Wen Sun

Proceedings of the International Conference on Machine Learning, 2022

Estimating Structural Disparities for Face Models.

Shervin Ardeshir, Cristina Segalin, Nathan Kallus

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Stateful Offline Contextual Policy Evaluation and Learning.

Nathan Kallus, Angela Zhou

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Minimax-Optimal Policy Learning Under Unobserved Confounding.

Nathan Kallus, Angela Zhou

Manag. Sci., 2021

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

Jacob Dorn, Kevin Guo, Nathan Kallus

CoRR, 2021

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

Angela Zhou, Andrew Koo, Nathan Kallus, Rene Ropac, Richard Peterson, Stephen Koppel, Tiffany Bergin

CoRR, 2021

Residual Overfit Method of Exploration.

James McInerney, Nathan Kallus

CoRR, 2021

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

Nathan Kallus, Xiaojie Mao, Masatoshi Uehara

CoRR, 2021

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

Masatoshi Uehara, Masaaki Imaizumi, Nan Jiang, Nathan Kallus, Wen Sun, Tengyang Xie

CoRR, 2021

Control Variates for Slate Off-Policy Evaluation.

Nikos Vlassis, Ashok Chandrashekar, Fernando Amat Gil, Nathan Kallus

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

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

Aurélien Bibaut, Nathan Kallus, Maria Dimakopoulou, Antoine Chambaz, Mark J. van der Laan

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Post-Contextual-Bandit Inference.

Aurélien Bibaut, Maria Dimakopoulou, Nathan Kallus, Antoine Chambaz, Mark J. van der Laan

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Optimal Off-Policy Evaluation from Multiple Logging Policies.

Nathan Kallus, Yuta Saito, Masatoshi Uehara

Proceedings of the 38th International Conference on Machine Learning, 2021

Fairness, Welfare, and Equity in Personalized Pricing.

Nathan Kallus, Angela Zhou

Proceedings of the FAccT '21: 2021 ACM Conference on Fairness, 2021

Fast Rates for the Regret of Offline Reinforcement Learning.

Yichun Hu, Nathan Kallus, Masatoshi Uehara

Proceedings of the Conference on Learning Theory, 2021

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

Andrew Bennett, Nathan Kallus, Lihong Li, Ali Mousavi

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

From Predictive to Prescriptive Analytics.

Dimitris Bertsimas, Nathan Kallus

Manag. Sci., 2020

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

Nathan Kallus, Masatoshi Uehara

J. Mach. Learn. Res., 2020

Generalized Optimal Matching Methods for Causal Inference.

Nathan Kallus

J. Mach. Learn. Res., 2020

Dynamic Assortment Personalization in High Dimensions.

Nathan Kallus, Madeleine Udell

Oper. Res., 2020

The Variational Method of Moments.

Andrew Bennett, Nathan Kallus

CoRR, 2020

Rejoinder: New Objectives for Policy Learning.

Nathan Kallus

CoRR, 2020

Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning.

Nathan Kallus, Masatoshi Uehara

CoRR, 2020

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

Yichun Hu, Nathan Kallus

CoRR, 2020

Comment: Entropy Learning for Dynamic Treatment Regimes.

Nathan Kallus

CoRR, 2020

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

Nathan Kallus, Xiaojie Mao

CoRR, 2020

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

Nathan Kallus, Angela Zhou

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

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

Nathan Kallus, Masatoshi Uehara

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Statistically Efficient Off-Policy Policy Gradients.

Nathan Kallus, Masatoshi Uehara

Proceedings of the 37th International Conference on Machine Learning, 2020

Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation.

Nathan Kallus, Masatoshi Uehara

Proceedings of the 37th International Conference on Machine Learning, 2020

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

Nathan Kallus

Proceedings of the 37th International Conference on Machine Learning, 2020

Efficient Policy Learning from Surrogate-Loss Classification Reductions.

Andrew Bennett, Nathan Kallus

Proceedings of the 37th International Conference on Machine Learning, 2020

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

Yichun Hu, Nathan Kallus, Xiaojie Mao

Proceedings of the Conference on Learning Theory, 2020

2019

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

Nathan Kallus, Xiaojie Mao, Masatoshi Uehara

CoRR, 2019

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

Nathan Kallus, Masatoshi Uehara

CoRR, 2019

More Efficient Policy Learning via Optimal Retargeting.

Nathan Kallus

CoRR, 2019

Assessing Disparate Impacts of Personalized Interventions: Identifiability and Bounds.

Nathan Kallus, Angela Zhou

CoRR, 2019

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

Nathan Kallus, Angela Zhou

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds.

Nathan Kallus, Angela Zhou

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

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

Nathan Kallus, Masatoshi Uehara

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Deep Generalized Method of Moments for Instrumental Variable Analysis.

Andrew Bennett, Nathan Kallus, Tobias Schnabel

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Policy Evaluation with Latent Confounders via Optimal Balance.

Andrew Bennett, Nathan Kallus

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Classifying Treatment Responders Under Causal Effect Monotonicity.

Nathan Kallus

Proceedings of the 36th International Conference on Machine Learning, 2019

Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved.

Jiahao Chen, Nathan Kallus, Xiaojie Mao, Geoffry Svacha, Madeleine Udell

Proceedings of the Conference on Fairness, Accountability, and Transparency, 2019

Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding.

Nathan Kallus, Xiaojie Mao, Angela Zhou

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Robust sample average approximation.

Dimitris Bertsimas, Vishal Gupta, Nathan Kallus

Math. Program., 2018

Data-driven robust optimization.

Dimitris Bertsimas, Vishal Gupta, Nathan Kallus

Math. Program., 2018

Confounding-Robust Policy Improvement.

Nathan Kallus, Angela Zhou

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Removing Hidden Confounding by Experimental Grounding.

Nathan Kallus, Aahlad Manas Puli, Uri Shalit

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Causal Inference with Noisy and Missing Covariates via Matrix Factorization.

Nathan Kallus, Xiaojie Mao, Madeleine Udell

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Balanced Policy Evaluation and Learning.

Nathan Kallus

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Residual Unfairness in Fair Machine Learning from Prejudiced Data.

Nathan Kallus, Angela Zhou

Proceedings of the 35th International Conference on Machine Learning, 2018

Instrument-Armed Bandits.

Nathan Kallus

Proceedings of the Algorithmic Learning Theory, 2018

Policy Evaluation and Optimization with Continuous Treatments.

Nathan Kallus, Angela Zhou

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017

Recursive Partitioning for Personalization using Observational Data.

Nathan Kallus

Proceedings of the 34th International Conference on Machine Learning, 2017

A Framework for Optimal Matching for Causal Inference.

Nathan Kallus

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

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

Nathan Kallus

Proceedings of the UAI 2016 Workshop on Causation: Foundation to Application co-located with the 32nd Conference on Uncertainty in Artificial Intelligence (UAI 2016), 2016

Revealed Preference at Scale: Learning Personalized Preferences from Assortment Choices.

Nathan Kallus, Madeleine Udell

Proceedings of the 2016 ACM Conference on Economics and Computation, 2016

2015

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

Dimitris Bertsimas, Mac Johnson, Nathan Kallus

Oper. Res., 2015

Learning Preferences from Assortment Choices in a Heterogeneous Population.

Nathan Kallus, Madeleine Udell

CoRR, 2015

2014

From Predictions to Data-Driven Decisions Using Machine Learning.

Nathan Kallus

CoRR, 2014

Predicting crowd behavior with big public data.

Nathan Kallus

Proceedings of the 23rd International World Wide Web Conference, 2014

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

Nathan Kallus

Proceedings of the Big Data Analytics in the Social and Ubiquitous Context, 2014