firstbacksecondback
22 Results
|
Workshop
|
Fri 6:30 |
Data-Efficient Training of Autoencoders for Mildly Non-Linear Problems Muhammad Al-Digeil |
|
|
Poster
|
Wed 1:00 |
Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time Yu Cheng · Honghao Lin |
|
|
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 |
|
|
Spotlight
|
Thu 19:35 |
What are the Statistical Limits of Offline RL with Linear Function Approximation? Ruosong Wang · Dean Foster · Sham M Kakade |
|
|
Oral
|
Wed 3:15 |
Rethinking Attention with Performers Krzysztof Choromanski · Valerii Likhosherstov · David Dohan · Xingyou Song · Georgiana-Andreea Gane · Tamas Sarlos · Peter Hawkins · Jared Q Davis · Afroz Mohiuddin · Lukasz Kaiser · David Belanger · Lucy J Colwell · Adrian Weller |
|
|
Poster
|
Wed 9:00 |
TropEx: An Algorithm for Extracting Linear Terms in Deep Neural Networks Martin Trimmel · Henning Petzka · Cristian Sminchisescu |
|
|
Poster
|
Thu 9:00 |
Linear Last-iterate Convergence in Constrained Saddle-point Optimization Chen-Yu Wei · Chung-Wei Lee · Mengxiao Zhang · Haipeng Luo |
|
|
Poster
|
Mon 17:00 |
What are the Statistical Limits of Offline RL with Linear Function Approximation? Ruosong Wang · Dean Foster · Sham M Kakade |
|
|
Poster
|
Tue 17:00 |
A unifying view on implicit bias in training linear neural networks Chulhee Yun · Shankar Krishnan · Hossein Mobahi |
|
|
Poster
|
Wed 17:00 |
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective Wuyang Chen · Xinyu Gong · Zhangyang Wang |
|
|
Poster
|
Tue 9:00 |
Rethinking Attention with Performers Krzysztof Choromanski · Valerii Likhosherstov · David Dohan · Xingyou Song · Georgiana-Andreea Gane · Tamas Sarlos · Peter Hawkins · Jared Q Davis · Afroz Mohiuddin · Lukasz Kaiser · David Belanger · Lucy J Colwell · Adrian Weller |
|
|
Poster
|
Mon 17:00 |
Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods Taiji Suzuki · Akiyama Shunta |