Skip to main content
Cyber Security and Resilience Technology
Cyber Security and Resilience Technology
Main navigation
Home
People
All Profiles
Leadership Team
Affiliate Faculty
Research Scientists
Research Staff
Postdoctoral Fellows
Students
Team
Projects
Startups
Datasets
Broximal Point Method
The Broximal Point Method and Its Impact on Optimization Theory and Machine Learning
Peter Richtarik, Professor, Computer Science
Sep 21, 12:00
-
13:00
B9 R2325
Broximal Point Method
proximal algorithms
machine learning
gradient methods
This talk introduces the Broximal Point Method (BPM), a condition-number-free alternative to classical proximal methods, that replaces proximal penalties with ball constraints, surveys its theoretical extensions and distributed variants, and explains how approximate non-Euclidean Brox updates underpin practical machine learning optimizers.
