Use of static surrogates in hyperparameter optimization
Abstract: Optimizing the hyperparameters and architecture of a neural network is a long yet necessary phase in the development of any new application. This consuming process can benefit from the elaboration of strategies designed to quickly discard low quality configurations and focus on more promising candidates. This work aims at enhancing HyperNOMAD, a library that adapts a direct search derivative-free optimization algorithm to tune both the architecture and the training of a neural network simultaneously, by targeting two keys steps of its execution and exploiting cheap approximations in the form of static surrogates to trigger the early stopping of the evaluation of a configuration and the ranking of pools of candidates. These additions to HyperNOMAD are shown to improve on its resources consumption without harming the quality of the proposed solutions.
Keywords: Hyperparameter optimization (HPO), Derivative-free optimization (DFO), Blackbox optimization (BBO).
Category 1: Nonlinear Optimization
Category 2: Optimization Software and Modeling Systems
Citation: Les Cahiers du GERAD G-2021-XX.
Entry Submitted: 03/14/2021
Modify/Update this entry
|Visitors||Authors||More about us||Links|
Search, Browse the Repository
Give us feedback
|Optimization Journals, Sites, Societies|