arXiv:2002.11429
공식 코드 · Papers with Code
PHS: A Toolbox for Parallel Hyperparameter Search
원문 초록
We introduce an open source python framework named PHS - Parallel Hyperparameter Search to enable hyperparameter optimization on numerous compute instances of any arbitrary python function. This is achieved with minimal modifications inside the target function. Possible applications appear in expensive to evaluate numerical computations which strongly depend on hyperparameters such as machine learning. Bayesian optimization is chosen as a sample efficient method to propose the next query set of parameters.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms
BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL
Interim Report on Human-Guided Adaptive Hyperparameter Optimization with Multi-Fidelity Sprints
HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings
Clustering-based Meta Bayesian Optimization with Theoretical Guarantee
ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.