arXiv:2012.08180
공식 코드 · Papers with Code
Squirrel: A Switching Hyperparameter Optimizer
원문 초록
In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach switches between different optimizers. Since the team names on the competition's leaderboard were randomly generated "alliteration nicknames", consisting of an adjective and an animal with the same initial letter, we called our approach the Switching Squirrel, or here, short, Squirrel.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Overtuning in Hyperparameter Optimization
From Tiny Machine Learning to Tiny Deep Learning: A Survey
VirnyFlow: A Design Space for Responsible Model Development
OptiMindTune: A Multi-Agent Framework for Intelligent Hyperparameter Optimization
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger
토론
이 논문과 연결된 포럼 글이 아직 없습니다.