b'Nathan Kallus'

Control Variates for Slate Off-Policy Evaluation

We study the problem of off-policy evaluation from batched contextual ba...
06/15/2021 ∙ by Nikos Vlassis, et al. ∙ 0 ∙ share

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

Empirical risk minimization (ERM) is the workhorse of machine learning, ...
06/03/2021 ∙ by Aurélien Bibaut, et al. ∙ 7 ∙ share

read it
Post-Contextual-Bandit Inference

Contextual bandit algorithms are increasingly replacing non-adaptive A/B...
06/01/2021 ∙ by Aurélien Bibaut, et al. ∙ 1 ∙ share

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...
03/25/2021 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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

We offer a theoretical characterization of off-policy evaluation (OPE) i...
02/05/2021 ∙ by Masatoshi Uehara, et al. ∙ 2 ∙ share

read it
Fast Rates for the Regret of Offline Reinforcement Learning

We study the regret of reinforcement learning from offline data generate...
01/31/2021 ∙ by Yichun Hu, et al. ∙ 15 ∙ share

read it
Fairness, Welfare, and Equity in Personalized Pricing

We study the interplay of fairness, welfare, and equity considerations i...
12/21/2020 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
The Variational Method of Moments

The conditional moment problem is a powerful formulation for describing ...
12/17/2020 ∙ by Andrew Bennett, et al. ∙ 7 ∙ share

read it
Rejoinder: New Objectives for Policy Learning

I provide a rejoinder for discussion of "More Efficient Policy Learning ...
12/05/2020 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Fast Rates for Contextual Linear Optimization

Incorporating side observations of predictive features can help reduce u...
11/05/2020 ∙ by Yichun Hu, et al. ∙ 1 ∙ share

read it
Optimal Off-Policy Evaluation from Multiple Logging Policies

We study off-policy evaluation (OPE) from multiple logging policies, eac...
10/21/2020 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Stochastic Optimization Forests

We study conditional stochastic optimization problems, where we leverage...
08/17/2020 ∙ by Nathan Kallus, et al. ∙ 21 ∙ share

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

Off-policy evaluation (OPE) in reinforcement learning is an important pr...
07/27/2020 ∙ by Andrew Bennett, et al. ∙ 5 ∙ share

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

Offline reinforcement learning, wherein one uses off-policy data logged ...
06/06/2020 ∙ by Nathan Kallus, et al. ∙ 15 ∙ share

read it
Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning

We study the efficient off-policy evaluation of natural stochastic polic...
06/06/2020 ∙ by Nathan Kallus, et al. ∙ 4 ∙ share

read it
On the Optimality of Randomization in Experimental Design: How to Randomize for Minimax Variance and Design-Based Inference

I study the minimax-optimal design for a two-arm controlled experiment w...
05/06/2020 ∙ by Nathan Kallus, et al. ∙ 4 ∙ share

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

Dynamic treatment regimes (DTRs) for are personalized, sequential treatm...
05/06/2020 ∙ by Yichun Hu, et al. ∙ 5 ∙ share

read it
Comment: Entropy Learning for Dynamic Treatment Regimes

I congratulate Profs. Binyan Jiang, Rui Song, Jialiang Li, and Donglin Z...
04/06/2020 ∙ by Nathan Kallus, et al. ∙ 3 ∙ share

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...
03/27/2020 ∙ by Nathan Kallus, et al. ∙ 2 ∙ share

read it
Efficient Policy Learning from Surrogate-Loss Classification Reductions

Recent work on policy learning from observational data has highlighted t...
02/12/2020 ∙ by Andrew Bennett, et al. ∙ 11 ∙ share

read it
Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning

Off-policy evaluation of sequential decision policies from observational...
02/11/2020 ∙ by Nathan Kallus, et al. ∙ 8 ∙ share

read it
Statistically Efficient Off-Policy Policy Gradients

Policy gradient methods in reinforcement learning update policy paramete...
02/10/2020 ∙ by Nathan Kallus, et al. ∙ 26 ∙ share

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...
01/21/2020 ∙ by Fredrik D. Johansson, et al. ∙ 89 ∙ share

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 low-dimensional parameter in t...
12/30/2019 ∙ by Nathan Kallus, et al. ∙ 13 ∙ share

read it
Balanced Policy Evaluation and Learning for Right Censored Data

Individualized treatment rules can lead to better health outcomes when p...
11/13/2019 ∙ by Owen E. Leete, et al. ∙ 0 ∙ share

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...
10/26/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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

Off-policy evaluation (OPE) in reinforcement learning is notoriously dif...
09/12/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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

We study a nonparametric contextual bandit problem where the expected re...
09/05/2019 ∙ by Yichun Hu, et al. ∙ 0 ∙ share

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

Off-policy evaluation (OPE) in reinforcement learning allows one to eval...
08/22/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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...
08/13/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Policy Evaluation with Latent Confounders via Optimal Balance

Evaluating novel contextual bandit policies using logged data is crucial...
08/06/2019 ∙ by Andrew Bennett, et al. ∙ 0 ∙ share

read it
More Efficient Policy Learning via Optimal Retargeting

Policy learning can be used to extract individualized treatment regimes ...
06/20/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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

Off-policy evaluation (OPE) in both contextual bandits and reinforcement...
06/09/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Assessing Disparate Impacts of Personalized Interventions: Identifiability and Bounds

Personalized interventions in social services, education, and healthcare...
06/04/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination

The increasing impact of algorithmic decisions on people's lives compels...
06/01/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Data-Pooling in Stochastic Optimization

Managing large-scale systems often involves simultaneously solving thous...
06/01/2019 ∙ by Vishal Gupta, et al. ∙ 0 ∙ share

read it
Deep Generalized Method of Moments for Instrumental Variable Analysis

Instrumental variable analysis is a powerful tool for estimating causal ...
05/29/2019 ∙ by Andrew Bennett, et al. ∙ 0 ∙ share

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

Where machine-learned predictive risk scores inform high-stakes decision...
02/15/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Classifying Treatment Responders Under Causal Effect Monotonicity

In the context of individual-level causal inference, we study the proble...
02/14/2019 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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...
11/27/2018 ∙ by Jiahao Chen, et al. ∙ 0 ∙ share

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...
11/10/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Removing Hidden Confounding by Experimental Grounding

Observational data is increasingly used as a means for making individual...
10/27/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding

We study the problem of learning conditional average treatment effects (...
10/05/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Residual Unfairness in Fair Machine Learning from Prejudiced Data

Recent work in fairness in machine learning has proposed adjusting for f...
06/07/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Optimal Balancing of Time-Dependent Confounders for Marginal Structural Models

Marginal structural models (MSMs) estimate the causal effect of a time-v...
06/04/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Causal Inference with Noisy and Missing Covariates via Matrix Factorization

Valid causal inference in observational studies often requires controlli...
06/03/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Confounding-Robust Policy Improvement

We study the problem of learning personalized decision policies from obs...
05/22/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it
Learning Weighted Representations for Generalization Across Designs

Predictive models that generalize well under distributional shift are of...
02/23/2018 ∙ by Fredrik D. Johansson, et al. ∙ 0 ∙ share

read it
Policy Evaluation and Optimization with Continuous Treatments

We study the problem of policy evaluation and learning from batched cont...
02/16/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

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

We study optimal covariate balance for causal inferences from observatio...
02/15/2018 ∙ by Nathan Kallus, et al. ∙ 0 ∙ share

read it

Nathan Kallus

Featured Co-authors