6 papers
Algorithms for adaptive and heteroskedastic linear regression at the computational threshold
Spencer Compton, Tselil Schramm
We study finite-sample linear regression in the presence of varied and unknown label noise, focusing on the heteroskedastic and adaptive linear regression models. Heteroskedastic l…
Efficient -approximate minimum-entropy couplings
Spencer Compton
Given discrete probability distributions over states each, the minimum-entropy coupling is the minimum-entropy joint distribution whose marginals are the same as the…
Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more
Spencer Compton, Jerry Li
We study the task of density estimation, where we hope to accurately estimate a probability density from samples. A textbook method for density estimation in total variation di…
Ratio Covers of Convex Sets and Optimal Mixture Density Estimation
Spencer Compton, Gábor Lugosi, Jaouad Mourtada +2
We study density estimation in Kullback-Leibler divergence: given an i.i.d. sample from an unknown density , the goal is to construct an estimator such that…
Attainability of Two-Point Testing Rates for Finite-Sample Location Estimation
Spencer Compton, Gregory Valiant
Le Cam's two-point testing method yields perhaps the simplest lower bound for estimating the mean of a distribution: roughly, if it is impossible to well-distinguish a distribution…
High-Accuracy List-Decodable Mean Estimation
Ziyun Chen, Spencer Compton, Daniel Kane +1
In list-decodable learning, we are given a set of data points such that an -fraction of these points come from a nice distribution , for some small , and the goal i…