Patent · US Active

Hyperparameter determination for a differentially private federated learning process

US11941520B2 · kind B2 · utility

1Cited by
3References
25Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 9, 2020
Grant dateMar 26, 2024
Priority date
Expiry dateJul 3, 2042

Classification

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

Abstract

Techniques regarding determining hyperparameters for a differentially private federated learning process are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a hyperparameter advisor component that determines a hyperparameter for a model of a differentially private federated learning process based on a defined numeric relationship between a privacy budget, a learning rate schedule, and a batch size.

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