research
∙
07/21/2023
Bandits with Deterministically Evolving States
We propose a model for learning with bandit feedback while accounting fo...
share
research
∙
12/01/2021
Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls
We investigate the optimal design of experimental studies that have pre-...
research
∙
02/25/2021
Batched Neural Bandits
In many sequential decision-making problems, the individuals are split i...
research
∙
02/24/2020
Optimal and Greedy Algorithms for Multi-Armed Bandits with Many Arms
We characterize Bayesian regret in a stochastic multi-armed bandit probl...
research
∙
01/11/2019
Non-Parametric Inference Adaptive to Intrinsic Dimension
We consider non-parametric estimation and inference of conditional momen...
research
∙
10/27/2017
Matrix Completion Methods for Causal Panel Data Models
In this paper we develop new methods for estimating causal effects in se...
research
∙
04/28/2017
Exploiting the Natural Exploration In Contextual Bandits
The contextual bandit literature has traditionally focused on algorithms...
research
∙
11/04/2016