firstbacksecondback
125 Results
|
Spotlight
|
Mon 13:40 |
Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models Zirui Wang · Yulia Tsvetkov · Orhan Firat · Yuan Cao |
|
|
Oral
|
Thu 0:30 |
Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime Atsushi Nitanda · Taiji Suzuki |
|
|
Oral
|
Tue 4:23 |
Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes Mike Gartrell · Insu Han · Elvis Dohmatob · Jennifer Gillenwater · Victor-Emmanuel Brunel |
|
|
Oral
|
Tue 12:00 |
Randomized Automatic Differentiation Deniz Oktay · Nick McGreivy · Joshua Aduol · Alex Beatson · Ryan P Adams |
|
|
Spotlight
|
Wed 5:15 |
Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods Taiji Suzuki · Akiyama Shunta |
|
|
Oral
|
Mon 11:00 |
Federated Learning Based on Dynamic Regularization Durmus Alp Emre Acar · Yue Zhao · Ramon Matas · Matthew Mattina · Paul Whatmough · Venkatesh Saligrama |
|
|
Spotlight
|
Wed 19:15 |
GAN "Steerability" without optimization Nurit Spingarn Eliezer · Ron Banner · Tomer Michaeli |
|
|
Spotlight
|
Tue 21:43 |
Memory Optimization for Deep Networks Aashaka Shah · Chao-Yuan Wu · Jayashree Mohan · Vijay Chidambaram · Philipp Krähenbühl |
|
|
Spotlight
|
Tue 12:40 |
Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time Tolga Ergen · Mert Pilanci |
|
|
Spotlight
|
Mon 3:30 |
Deciphering and Optimizing Multi-Task Learning: a Random Matrix Approach Malik Tiomoko · Hafiz Tiomoko Ali · Romain Couillet |
|
|
Spotlight
|
Wed 21:25 |
Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control Zhuang Liu · Xuanlin Li · Bingyi Kang · trevor darrell |
|
|
Poster
|
Thu 17:00 |
Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity Shaocong Ma · Ziyi Chen · Yi Zhou · Shaofeng Zou |