Orals and spotlights
in
Workshop: OPT 2021: Optimization for Machine Learning

Contributed talks in Session 4 (Zoom)

Quanquan Gu ⋅ Agnieszka Słowik ⋅ Jacques Chen ⋅ Neha Wadia ⋅ Difan Zou

Oral (10 min)

On the Relation between Distributionally Robust Optimization and Data Curation, Agnieszka Slowik

Spotlights (5 min)

Heavy-tailed noise does not explain the gap between SGD and Adam on Transformers, Jacques Chen
Optimization with Adaptive Step Size Selection from a Dynamical Systems Perspective, Neha Wadia
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization, Difan Zou

There will be a Q&A in the last 5 minutes for all speakers. Abstracts for the talks are below the schedule.

Chat is not available.