Skip to main content
Communication and Computing Systems Lab
Communication and Computing Systems Lab
Home
People
All Profiles
Principal Investigator
Postdoctoral Fellows
Research Scientists
Research Staff
Students
Alumni
Former Members
Research
Wireless Communication
Body Area Network
Applied Artificial Intelligence
All Projects
Publications
Publications
Google Scholar
DBLP
IEEE Xplore
KAUST Repository
ORCID
Events
Media Gallery
Contacts
News
Join us
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.
