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

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. al. , 2022). This optimality is defined in terms of iteration and oracle complexity, as well as the maximal admissible level of adversarial noise. However, the assumption of finite variance is burdensome and it might not hold in many practical scenarios. To address this, we demonstrate how to adapt a refined clipped version of the accelerated gradient (Stochastic Similar Triangles) method from (Sadiev et al. , 2023) for a two-point zero-order oracle. This adaptation entails extending the batching technique to accommodate infinite variance — a non-trivial task that stands as a distinct contribution of this paper.

Authors

• Nikita Kornilov
• Ohad Shamir Microsoft Research
• Aleksandr Lobanov
• Darina Dvinskikh
• Alexander Gasnikov Research Center of the Artificial Intelligence Institute, Innopolis University, Innopolis, Russia MIPT ISP RAS
• Innokentiy Shibaev
• Eduard Gorbunov
• Samuel Horváth

Keywords

No keywords are indexed for this paper.