Aleksandr Lobanov — accepted AI-conference papers

2024

Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values

Aleksandr Lobanov, Alexander Gasnikov, Andrey Krasnov

NeurIPS 2024poster

Frequently, the burgeoning field of black-box optimization encounters challenges due to a limited understanding of the mechanisms of the objective function. To address such problems, in this work we focus on the deterministic concept of Order Oracle, which only utilizes order access between function…

Cited by 6 Source ↗PDF ↗Scholar ↗

2023

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

Nikita Kornilov, Ohad Shamir, Aleksandr Lobanov, Darina Dvinskikh, Alexander Gasnikov, Innokentiy Andreevich Shibaev +2

NeurIPS 2023poster

In this paper, we consider non-smooth stochastic convex optimization with two function evaluations per round under infinite noise variance. In the classical setting when noise has finite variance, an optimal algorithm, built upon the batched accelerated gradient method, was proposed in (Gasnikov et.…

Cited by 12 Source ↗PDF ↗code ↗Scholar ↗