… Luc Devroye McGill University Abbas Mehrabian† McGill University Tommy Reddad‡
McGill University … Email: abbas.mehrabian@gmail.com. ‡Supported by NSERC PGS D …

Let A be an isotropic, sub-gaussian m × n matrix. We prove that the process \documentclass[12pt]{minimal}
\usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \…

We study a multiplayer stochastic multi-armed bandit problem in which players cannot
communicate, and if two or more players pull the same arm, a collision occurs and the involved …

We prove new upper and lower bounds on the VC-dimension of deep neural networks with
the ReLU activation function. These bounds are tight for almost the entire range of …

In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially
enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling …

We consider PAC learning of probability distributions (aka density estimation), where we
are given an iid sample generated from an unknown target distribution, and want to output a …

We present simple algorithms for batched stochastic multi-armed bandit and batched
stochastic linear bandit problems. We prove bounds for their expected regrets that improve and …

We prove that ϴ (kd^ 2/ε^ 2) samples are necessary and sufficient for learning a mixture of k
Gaussians in R^ d, up to error ε in total variation distance. This improves both the known …

We introduce a novel technique for distribution learning based on a notion of sample
compression. Any class of distributions that allows such a compression scheme can be learned …

We study multiplayer stochastic multiarmed bandit problems in which the players cannot
communicate, and if two or more players pull the same arm, a collision occurs and the involved …