Research index
Anonymous Code for Lamda Framework
Anonymous
Zenodo (CERN European Organization for Nuclear Research)2 Dec 2024Open access
NobleIDark:/48914/w1/20260521/A9B2502FDOI10.5281/zenodo.14261996
Anonymous Code for Lamda Framework
Anonymous · Zenodo (CERN European Organization for Nuclear Research) · 2024
NobleIDark:/48914/w1/20260521/A9B2502FDOI10.5281/zenodo.14261996
Free to read at the publisher
You can read the abstract here, or the full text at the publisher.
Abstract
This repository contains pseudocode and implementation for the submitted paper "LAMDA: Two-Phase Multi-Fidelity HPO via Learning Promising Regions from Data". The code has been anonymized to comply with the review process. Currently, we provide implementations for the following methods used in hyperparameter optimization (HPO): Lamda+BOHB and BOHBLamda+MUMBO and MUMBOLamda+BO and BOLamda+RS and RSWe utilized the following packages for our implementations: HpBandSter for BOHB and RS: https://github.com/automl/HpBandSterEmukit for MUMBO: https://github.com/EmuKit/emukit/blob/main/notebooks/Emukit-tutorial-multi-fidelity-MUMBO-Example.ipynbGPyOpt for Bayesian Optimization (BO): https://github.com/SheffieldML/GPyOpt