International Business Machines Corporation

Colin Sutcher-Shepard

Gegi Thomas

Jayaram Kallapalayam Radhakrishnan

Ashish Verma

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.

Growing community of inventors

Troy, NY, United States of America

Colin Sutcher-Shepard