AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration
원문 초록
We study the algorithm configuration (AC) problem, in which one seeks to find an optimal parameter configuration of a given target algorithm in an automated way. Recently, there has been significant progress in designing AC approaches that satisfy strong theoretical guarantees. However, a significant gap still remains between the practical performance of these approaches and state-of-the-art heuristic methods. To this end, we introduce AC-Band, a general approach for the AC problem based on multi-armed bandits that provides theoretical guarantees while exhibiting strong practical performance. We show that AC-Band requires significantly less computation time than other AC approaches providing theoretical guarantees while still yielding high-quality configurations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance Adaptation
VirnyFlow: A Design Space for Responsible Model Development
Test-Time Scaling of Diffusion Models via Noise Trajectory Search
Human in the Loop Adaptive Optimization for Improved Time Series Forecasting
Antithetic Sampling for Top-k Shapley Identification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.