Search All 2021 Events
  Search abstracts

Filter by Keyword:

9 Results

<<   <   Page 1 of 1   >>   >
Poster
Mon 9:00 On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
Marius Mosbach · Maksym Andriushchenko · Dietrich Klakow
Poster
Tue 9:00 Physics-aware, probabilistic model order reduction with guaranteed stability
Sebastian Kaltenbach · PS Koutsourelakis
Poster
Wed 9:00 DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Xiangxiang Chu · Victor Wang · Bo Zhang · Shun Lu · Xiaolin Wei · Junchi Yan
Poster
Tue 17:00 Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
Jeremy Cohen · Simran Kaur · Yuanzhi Li · Zico Kolter · Ameet Talwalkar
Poster
Mon 17:00 Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients
Jing An · Lexing Ying · Yuhua Zhu
Poster
Wed 9:00 Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies
T. Konstantin Rusch · Siddhartha Mishra
Poster
Wed 17:00 Estimating informativeness of samples with Smooth Unique Information
Hrayr Harutyunyan · Alessandro Achille · Giovanni Paolini · Orchid Majumder · Avinash Ravichandran · Rahul Bhotika · Stefano Soatto
Oral
Wed 12:23 Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies
T. Konstantin Rusch · Siddhartha Mishra
Workshop
Mitigating Adversarial Training Instability with Batch Normalization
Arvind Sridhar