5 papers
Sharp Minimax Theory for Randomized Experiments
Timothy Sudijono, Edgar Dobriban, Eric Tchetgen Tchetgen
We study minimax-optimal designs and estimators for estimating the sample average treatment effect in finite population randomized experiments, where both design and estimator are…
Regression Adjustments for Double Randomization in Two-Sided Marketplaces
Timothy Sudijono, Lihua Lei, Lorenzo Masoero +3
Multiple randomization designs (MRDs) are a class of experimental designs used to handle interference in two-sided marketplaces. We investigate regression adjustment strategies for…
Compound Selection Decisions: An Almost SURE Approach
Jiafeng Chen, Lihua Lei, Timothy Sudijono +2
This paper proposes methods for producing compound selection decisions in a Gaussian sequence model. Given unknown, fixed parameters and known with observation…
Non-identifiability distinguishes Neural Networks among Parametric Models
Sourav Chatterjee, Timothy Sudijono
One of the enduring problems surrounding neural networks is to identify the factors that differentiate them from traditional statistical models. We prove a pair of results which di…
Neural Networks Generalize on Low Complexity Data
Sourav Chatterjee, Timothy Sudijono
We show that feedforward neural networks with ReLU activation generalize on low complexity data, suitably defined. Given i.i.d.~data generated from a simple programming language, t…