P. R. Gerber

collaborators

4 papers

math.ST2023

Density estimation using the perceptron

Patrik Róbert Gerber, Tianze Jiang, Yury Polyanskiy +1

We propose a new density estimation algorithm. Given $n$ i.i.d. observations from a distribution belonging to a class of densities on $R^{d}$ , our estimator outputs any dens…

stat.ML2023

Kernel-Based Tests for Likelihood-Free Hypothesis Testing

Patrik Róbert Gerber, Tianze Jiang, Yury Polyanskiy +1

Given $n$ observations from two balanced classes, consider the task of labeling an additional $m$ inputs that are known to all belong to \emph{one} of the two classes. Special case…

math.ST2023

Minimax optimal testing by classification

Patrik Róbert Gerber, Yanjun Han, Yury Polyanskiy

This paper considers an ML inspired approach to hypothesis testing known as classifier/classification-accuracy testing ( $CAT$ ). In $CAT$ , one first trains a class…

math.ST2022

Likelihood-free hypothesis testing

Patrik Róbert Gerber, Yury Polyanskiy

Consider the problem of binary hypothesis testing. Given $Z$ coming from either $P^{\otimes m}$ or $Q^{\otimes m}$ , to decide between the two with small probability…