collaborators

6 papers

math.ST2026

Generalized bootstrap in the Bures-Wasserstein space

Alexey Kroshnin, Vladimir Spokoiny, Alexandra Suvorikova

This study proposes a bootstrap-based method for uncertainty quantification in two important statistical scenarios. First, we approximate the sampling distribution of empirical bar…

math.OC2026

Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity

Alexandra Suvorikova, Igor Pavlov, Artem Vasin +4

Zeroth-order (black-box) optimization is applied when gradients are unavailable and objective evaluations rely on expensive simulations. In many such applications, the oracle fidel…

cs.LG2026

SLDP: Semi-Local Differential Privacy for Density-Adaptive Analytics

Alexey Kroshnin, Alexandra Suvorikova

Density-adaptive domain discretization is essential for high-utility privacy-preserving analytics but remains challenging under Local Differential Privacy (LDP) due to the privacy-…

q-bio.QM2026

friends.test: rank-based method for feature selection in interaction matrices

Alexandra Suvorikova, Alexey Kroshnin, Dmirijs Lvovs +5

The analysis of the interaction matrix between two distinct sets is essential across diverse fields, from pharmacovigilance to transcriptomics. Not all interactions are equally inf…

cs.LG2026

UCB-type Algorithm for Budget-Constrained Expert Learning

Ilgam Latypov, Alexandra Suvorikova, Alexey Kroshnin +2

In many modern applications, a system must dynamically choose between several adaptive learning algorithms that are trained online. Examples include model selection in streaming en…

math.PR2025

Bernstein-type and Bennett-type inequalities for unbounded matrix martingales

Alexey Kroshnin, Alexandra Suvorikova

We derive explicit Bernstein-type and Bennett-type concentration inequalities for matrix-valued martingale processes with unbounded observations from the Hermitian space $\mathbb{H…