6 papers
Improved Analysis of Adaptive Task Allocation and Non-Stationary Processing Times
Grigory Begunov, Ilgam Latypov, Yuriy Dorn +1
We study the task allocation problem, where our goal is to develop an online algorithm that efficiently distributes tasks among workers based on their computational performance. Th…
Localize, Restart, Accelerate: Stochastic Optimization under Generalized Smoothness
Darina Dvinskikh, Alexander Gasnikov, Aleksandr Lobanov +1
We study stochastic convex optimization under asymmetric \((L_0,L_1)\)-generalized smoothness, a model motivated by machine-learning objectives whose local curvature may grow with…
Managing Self-Learning Experts under Per-Round Budget Constraints
Ilgam Latypov, Alexandra Suvorikova, Alexey Kroshnin +2
This paper addresses the problem of sequential decision-making under learning budget constraints. Such settings naturally arise in applications like managing a portfolio of bandit…
Functional multi-armed bandit and the best function identification problems
Yuriy Dorn, Aleksandr Katrutsa, Ilgam Latypov +1
Bandit optimization usually refers to the class of online optimization problems with limited feedback, namely, a decision maker uses only the objective value at the current point t…
EEvA: Fast Expert-Based Algorithms for Buffer Page Replacement
Alexander Demin, Yuriy Dorn, Aleksandr Katrutsa +4
Optimal page replacement is an important problem in efficient buffer management. The range of replacement strategies known in the literature varies from simple but efficient FIFO-b…
Fast UCB-type algorithms for stochastic bandits with heavy and super heavy symmetric noise
Yuriy Dorn, Aleksandr Katrutsa, Ilgam Latypov +1
In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle.…