NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.
@TillFetzer and myself (@lage2104 ) implemented 4 multi-fidelity optimizers to NASLib.
These are: Successive Halving, Hyperband, Bayesian Optimization Hyperband and Differential Evolution Hyperband.
The implementation is mainly based on https://github.com/automl/nas-bench-x11.
Their implementation has been improved to run stable in NASLib.
@TillFetzer and myself (@lage2104 ) implemented 4 multi-fidelity optimizers to NASLib. These are: Successive Halving, Hyperband, Bayesian Optimization Hyperband and Differential Evolution Hyperband. The implementation is mainly based on https://github.com/automl/nas-bench-x11. Their implementation has been improved to run stable in NASLib.