Patent · US Active

Resource-efficient techniques for repeated hyper-parameter optimization

US12333438B1 · kind B1 · utility

0Cited by

0References

20Claims

0Family size

Assignee

AMAZON TECHNOLOGIES, INC. · US

Inventors

Giovanni Zappella · Berlin, DE
Cedric Philippe Archambeau · Berlin, DE
David Salinas · Berlin, DE

Key dates

Filing date	Jun 30, 2021
Grant date	Jun 17, 2025
Priority date	—
Expiry date	Apr 18, 2044

Classification

Technology area (CPC G)Physics
CPC primaryG06N5/01
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A particular hyper-parameter combination (HPC) that was recommended for a first task is included in a collection of candidate HPCs evaluated for a second task. Hyper-parameter analysis iterations are conducted for the second task using the collection. In one of the iterations, the second task is executed using a first iteration-specific set of HPCs, including the particular HPC and one or more other members of the collection. One or more of the HPCs of the first iteration-specific set of HPCs are pruned to generate a second iteration-specific set of HPCs for a subsequent iteration. HPCs are selected for pruning based on a comparison of their results with the results obtained from the particular HPC that was recommended for the first task. A recommended HPC for the second task is identified based on results of the analysis iterations.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.