Skip to main content
Computer, Electrical and Mathematical Sciences and Engineering
Computer, Electrical and Mathematical Sciences and Engineering
Home
Study
Prospective Students
Current Students
Internship Opportunities
Research
Research Overview
Research Areas
Research Groups
Programs
Applied Mathematics and Computational Science
Computer Science
Electrical and Computer Engineering
Statistics
People
All People
Faculty
Affiliate Faculty
Instructional Faculty
Research Scientists
Research Staff
Postdoctoral Fellows
Students
Alumni
Administrative Staff
News
Events
About
Who We Are
Leadership Team
Apply
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.
