Baharan Mirzasoleiman
@baharanm.bsky.social
Assistant Professor of CS at UCLA
Machine learning, Optimization, Data-efficient learning
Machine learning, Optimization, Data-efficient learning
Reposted by Baharan Mirzasoleiman
(1/2) Ever wondered why Sharpness-Aware Minimization (SAM) yields greater generalization gains in vision than in NLP? I'll discuss this at UCLA's CS-201 seminar on February 18th, relating it to the balance of SAM's impact on logit statistics vs model geometry.
cs.ucla.edu/upcoming-eve...
cs.ucla.edu/upcoming-eve...
CS 201 | Hossein Mobahi, Google DeepMind | CS
cs.ucla.edu
February 7, 2025 at 6:57 PM
(1/2) Ever wondered why Sharpness-Aware Minimization (SAM) yields greater generalization gains in vision than in NLP? I'll discuss this at UCLA's CS-201 seminar on February 18th, relating it to the balance of SAM's impact on logit statistics vs model geometry.
cs.ucla.edu/upcoming-eve...
cs.ucla.edu/upcoming-eve...