Systems and methods for parallel exploration of a hyperparameter search space
US12271795B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 24, 2024 |
| Grant date | Apr 8, 2025 |
| Priority date | — |
| Expiry date | Dec 24, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system, method, and computer-program product includes selecting, by a controller node, a plurality of hyperparameter search points from a hyperparameter search space; instructing, by the controller node, one or more worker nodes to concurrently train a plurality of machine learning models for a target number of epochs using the plurality of hyperparameter search points; receiving, from the one or more worker nodes, a plurality of performance metrics that measure a performance of the plurality of machine learning models during the target number of epochs; and removing, by the controller node, one or more underperforming hyperparameter search points from the plurality of hyperparameter search points according to a pre-defined performance metric ranking criterion associated with the plurality of performance metrics.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.