firstbacksecondback
31 Results
Poster
|
Thu 1:00 |
Understanding the effects of data parallelism and sparsity on neural network training Namhoon Lee · Thalaiyasingam Ajanthan · Philip Torr · Martin Jaggi |
|
Poster
|
Wed 17:00 |
Measuring Massive Multitask Language Understanding Dan Hendrycks · Collin Burns · Steven Basart · Andy Zou · Mantas Mazeika · Dawn Song · Jacob Steinhardt |
|
Poster
|
Mon 1:00 |
Towards Impartial Multi-task Learning Liyang Liu · Yi Li · Zhanghui Kuang · Jing-Hao Xue · Yimin Chen · Wenming Yang · Qingmin Liao · Wei Zhang |
|
Poster
|
Wed 1:00 |
Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning Alihan Hüyük · Daniel Jarrett · Cem Tekin · Mihaela van der Schaar |
|
Poster
|
Thu 17:00 |
When Do Curricula Work? Xiaoxia (Shirley) Wu · Ethan Dyer · Behnam Neyshabur |
|
Poster
|
Mon 9:00 |
Understanding the failure modes of out-of-distribution generalization Vaishnavh Nagarajan · Anders J Andreassen · Behnam Neyshabur |
|
Poster
|
Tue 17:00 |
Understanding the role of importance weighting for deep learning Da Xu · Yuting Ye · Chuanwei Ruan |
|
Poster
|
Mon 1:00 |
LEAF: A Learnable Frontend for Audio Classification Neil Zeghidour · Olivier Teboul · Félix de Chaumont Quitry · Marco Tagliasacchi |
|
Poster
|
Tue 9:00 |
Are wider nets better given the same number of parameters? Anna Golubeva · Guy Gur-Ari · Behnam Neyshabur |
|
Poster
|
Mon 17:00 |
The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers Preetum Nakkiran · Behnam Neyshabur · Hanie Sedghi |
|
Poster
|
Wed 9:00 |
On the Bottleneck of Graph Neural Networks and its Practical Implications Uri Alon · Eran Yahav |
|
Poster
|
Tue 17:00 |
CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding Yanru Qu · Dinghan Shen · Yelong Shen · Sandra Sajeev · Weizhu Chen · Jiawei Han |