|
Poster
|
Mon 1:00
|
The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods
Louis THIRY · Michael Arbel · Eugene Belilovsky · Edouard Oyallon
|
|
|
Poster
|
Tue 1:00
|
A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
Grégoire Mialon · Dexiong Chen · Alexandre d'Aspremont · Julien Mairal
|
|
|
Poster
|
Mon 9:00
|
Effective Distributed Learning with Random Features: Improved Bounds and Algorithms
Yong Liu · Jiankun Liu · Shuqiang Wang
|
|
|
Poster
|
Wed 9:00
|
Sliced Kernelized Stein Discrepancy
Wenbo Gong · Yingzhen Li · José Miguel Hernández Lobato
|
|
|
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
|
|
|
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
|
|
|
Poster
|
Wed 1:00
|
A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
Leon Lang · Maurice Weiler
|
|
