
Control Variates for Slate OffPolicy Evaluation
We study the problem of offpolicy evaluation from batched contextual ba...
read it

Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
Empirical risk minimization (ERM) is the workhorse of machine learning, ...
read it

PostContextualBandit Inference
Contextual bandit algorithms are increasingly replacing nonadaptive A/B...
read it

Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach
We study the estimation of causal parameters when not all confounders ar...
read it

Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and FirstOrder Efficiency
We offer a theoretical characterization of offpolicy evaluation (OPE) i...
read it

Fast Rates for the Regret of Offline Reinforcement Learning
We study the regret of reinforcement learning from offline data generate...
read it

Fairness, Welfare, and Equity in Personalized Pricing
We study the interplay of fairness, welfare, and equity considerations i...
read it

The Variational Method of Moments
The conditional moment problem is a powerful formulation for describing ...
read it

Rejoinder: New Objectives for Policy Learning
I provide a rejoinder for discussion of "More Efficient Policy Learning ...
read it

Fast Rates for Contextual Linear Optimization
Incorporating side observations of predictive features can help reduce u...
read it

Optimal OffPolicy Evaluation from Multiple Logging Policies
We study offpolicy evaluation (OPE) from multiple logging policies, eac...
read it

Stochastic Optimization Forests
We study conditional stochastic optimization problems, where we leverage...
read it

Offpolicy Evaluation in InfiniteHorizon Reinforcement Learning with Latent Confounders
Offpolicy evaluation (OPE) in reinforcement learning is an important pr...
read it

Doubly Robust OffPolicy Value and Gradient Estimation for Deterministic Policies
Offline reinforcement learning, wherein one uses offpolicy data logged ...
read it

Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning
We study the efficient offpolicy evaluation of natural stochastic polic...
read it

On the Optimality of Randomization in Experimental Design: How to Randomize for Minimax Variance and DesignBased Inference
I study the minimaxoptimal design for a twoarm controlled experiment w...
read it

DTR Bandit: Learning to Make ResponseAdaptive Decisions With Low Regret
Dynamic treatment regimes (DTRs) for are personalized, sequential treatm...
read it

Comment: Entropy Learning for Dynamic Treatment Regimes
I congratulate Profs. Binyan Jiang, Rui Song, Jialiang Li, and Donglin Z...
read it

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data
We study the problem of estimating treatment effects when the outcome of...
read it

Efficient Policy Learning from SurrogateLoss Classification Reductions
Recent work on policy learning from observational data has highlighted t...
read it

ConfoundingRobust Policy Evaluation in InfiniteHorizon Reinforcement Learning
Offpolicy evaluation of sequential decision policies from observational...
read it

Statistically Efficient OffPolicy Policy Gradients
Policy gradient methods in reinforcement learning update policy paramete...
read it

Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects
Practitioners in diverse fields such as healthcare, economics and educat...
read it

Localized Debiased Machine Learning: Efficient Estimation of Quantile Treatment Effects, Conditional Value at Risk, and Beyond
We consider the efficient estimation of a lowdimensional parameter in t...
read it

Balanced Policy Evaluation and Learning for Right Censored Data
Individualized treatment rules can lead to better health outcomes when p...
read it

Kernel Optimal Orthogonality Weighting: A Balancing Approach to Estimating Effects of Continuous Treatments
Many scientific questions require estimating the effects of continuous t...
read it

Efficiently Breaking the Curse of Horizon: Double Reinforcement Learning in InfiniteHorizon Processes
Offpolicy evaluation (OPE) in reinforcement learning is notoriously dif...
read it

Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes
We study a nonparametric contextual bandit problem where the expected re...
read it

Double Reinforcement Learning for Efficient OffPolicy Evaluation in Markov Decision Processes
Offpolicy evaluation (OPE) in reinforcement learning allows one to eval...
read it

Optimal Estimation of Generalized Average Treatment Effects using Kernel Optimal Matching
In causal inference, a variety of causal effect estimands have been stud...
read it

Policy Evaluation with Latent Confounders via Optimal Balance
Evaluating novel contextual bandit policies using logged data is crucial...
read it

More Efficient Policy Learning via Optimal Retargeting
Policy learning can be used to extract individualized treatment regimes ...
read it

Intrinsically Efficient, Stable, and Bounded OffPolicy Evaluation for Reinforcement Learning
Offpolicy evaluation (OPE) in both contextual bandits and reinforcement...
read it

Assessing Disparate Impacts of Personalized Interventions: Identifiability and Bounds
Personalized interventions in social services, education, and healthcare...
read it

Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination
The increasing impact of algorithmic decisions on people's lives compels...
read it

DataPooling in Stochastic Optimization
Managing largescale systems often involves simultaneously solving thous...
read it

Deep Generalized Method of Moments for Instrumental Variable Analysis
Instrumental variable analysis is a powerful tool for estimating causal ...
read it

The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric
Where machinelearned predictive risk scores inform highstakes decision...
read it

Classifying Treatment Responders Under Causal Effect Monotonicity
In the context of individuallevel causal inference, we study the proble...
read it

Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
Assessing the fairness of a decision making system with respect to a pro...
read it

More robust estimation of sample average treatment effects using Kernel Optimal Matching in an observational study of spine surgical interventions
Inverse probability of treatment weighting (IPTW), which has been used t...
read it

Removing Hidden Confounding by Experimental Grounding
Observational data is increasingly used as a means for making individual...
read it

Interval Estimation of IndividualLevel Causal Effects Under Unobserved Confounding
We study the problem of learning conditional average treatment effects (...
read it

Residual Unfairness in Fair Machine Learning from Prejudiced Data
Recent work in fairness in machine learning has proposed adjusting for f...
read it

Optimal Balancing of TimeDependent Confounders for Marginal Structural Models
Marginal structural models (MSMs) estimate the causal effect of a timev...
read it

Causal Inference with Noisy and Missing Covariates via Matrix Factorization
Valid causal inference in observational studies often requires controlli...
read it

ConfoundingRobust Policy Improvement
We study the problem of learning personalized decision policies from obs...
read it

Learning Weighted Representations for Generalization Across Designs
Predictive models that generalize well under distributional shift are of...
read it

Policy Evaluation and Optimization with Continuous Treatments
We study the problem of policy evaluation and learning from batched cont...
read it

DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training
We study optimal covariate balance for causal inferences from observatio...
read it
Nathan Kallus
is this you? claim profile