activity
20242026
collaborators

7 papers

math.PR2026

MaxCut for Covariances

Gleb Smirnov

Let have a multivariate totally positive () law. We prove that $$ \sum_{i<j}\mathbb{E}\left[\left|\mathrm{Cov}(X_i,X_j \mid X_{[n]\s…

cs.AI2026

Deep belief networks are exact

Gleb Smirnov

We prove that every strictly positive probability distribution on \(\{-1,1\}^n\) is represented exactly by a sigmoid belief network with finite parameters. This answers a question…

math.PR2026

Random sets are close to low-discrepancy sets

Gleb Smirnov, Roman Vershynin

We show that a random sample from an arbitrary probability measure on is close to a low-discrepancy point set. Namely, after moving only a small fraction of the samp…

math.PR2026

Discrepancy and Fisher information

Gleb Smirnov, Roman Vershynin

We give an online algorithm that keeps a symmetric random walk inside a convex body by discarding some of its steps. The expected number of discarded steps is controlled by a Fishe…

math.PR2025

Thinning to improve two-sample discrepancy

Gleb Smirnov, Roman Vershynin

The discrepancy between two independent samples \(X_1,\dots,X_n\) and \(Y_1,\dots,Y_n\) drawn from the same distribution on typically has order \(O(\sqrt{n})\) even…

math.ST2025

Improving discrepancy by moving a few points

Gleb Smirnov, Roman Vershynin

We show how to improve the discrepancy of an iid sample by moving only a few points. Specifically, modifying \( O(m) \) sample points on average reduces the Kolmogorov-Smirnov dist…