4 papers
A Scalable Nystrom-Based Kernel Two-Sample Test with Permutations
Antoine Chatalic, Marco Letizia, Nicolas Schreuder +1
Two-sample hypothesis testing-determining whether two sets of data are drawn from the same distribution-is a fundamental problem in statistics and machine learning with broad scien…
Minimax-Optimal Two-Sample Test with Sliced Wasserstein
Binh Thuan Tran, Nicolas Schreuder
We study the problem of nonparametric two-sample testing using the sliced Wasserstein (SW) distance. While prior theoretical and empirical work indicates that the SW distance offer…
The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks
Sholom Schechtman, Nicolas Schreuder
We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large clas…
Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling
Antoine Chatalic, Nicolas Schreuder, Ernesto De Vito +1
In this work we consider the problem of numerical integration, i.e., approximating integrals with respect to a target probability measure using only pointwise evaluations of the in…