Non-stationary Experimental Design under Linear Trends

Authors: David Simchi-Levi, Chonghuan Wang, Zeyu Zheng

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we address the problem of nonstationary experimental design under linear trends by considering two objectives: estimating the dynamic treatment effect and minimizing welfare loss within the experiment. We propose an efficient design that can be customized for optimal estimation error rate, optimal regret rate, or the Pareto optimal trade-off between the two objectives. We establish information-theoretical lower bounds that highlight the inherent challenge in estimating dynamic treatment effects and minimizing welfare loss, and also statistically reveal the fundamental trade-off between them.
Researcher Affiliation Academia David Simchi-Levi , Chonghuan Wang , Zeyu Zheng Institute for Data, Systems, and Society, Department of Civil and Environmental Engineering, Operations Research Center, MIT Laboratory for Information and Decision Systems, MIT Department of Industrial Engineering and Operations Research, University of California, Berkeley dslevi@mit.edu, chwang9@mit.edu, zyzheng@berkeley.edu
Pseudocode Yes Algorithm 1: Linear Exploration and OFU (L-EOFU)
Open Source Code No The paper does not contain any explicit statement about providing source code for the described methodology or a link to a code repository.
Open Datasets No This paper is theoretical and does not conduct experiments with datasets, thus it does not provide concrete access information for a publicly available or open dataset for training.
Dataset Splits No This paper is theoretical and does not conduct experiments, therefore it does not specify dataset splits for reproduction.
Hardware Specification No The paper does not provide specific details about the hardware used, as it focuses on theoretical contributions rather than empirical experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers, as it is a theoretical work and does not describe an empirical implementation.
Experiment Setup No The paper describes a theoretical design and analysis, but it does not include details about an experimental setup, hyperparameters, or training configurations.