5 papers
Finite-sample nonparametric mean tests: Leave-one-out duality and asymptotic optimality
Yifan Zhu, John C. Duchi
We study finite-sample valid tests of the one-sided mean hypothesis against for nonnegative random variables. To do so, we develop a leave-one-out dual cert…
A Bitter Lesson for Data Filtering
Christopher Mohri, John Duchi, Tatsunori Hashimoto
We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an apparently common belief that fil…
Prior Diffusiveness and Regret in the Linear-Gaussian Bandit
Yifan Zhu, John C. Duchi, Benjamin Van Roy
We prove that Thompson sampling exhibits Bayesian regret in the linear-Gaussian bandit with a prior d…
Distribution free M-estimation
Felipe Areces, John C. Duchi
The basic question of delineating those statistical problems that are solvable without making any assumptions on the underlying data distribution has long animated statistics and l…
A Few Observations on Sample-Conditional Coverage in Conformal Prediction
John C. Duchi
We revisit the problem of constructing predictive confidence sets for which we wish to obtain some type of conditional validity. We provide new arguments showing how ``split confor…