On the Complexity of Learning with Kernels thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

On the Complexity of Learning with Kernels

Published on Aug 20, 20151829 Views

A well-recognized limitation of kernel learning is the requirement to handle a kernel matrix, whose size is quadratic in the number of training examples. Many methods have been proposed to reduce this

Related categories

Chapter list

On the Complexity of Learning with Kernels00:00
Kernel Learning - 100:21
Kernel Learning - 200:27
Kernel Learning - 300:50
Making Kernels More Efficient01:20
Budget Constraints - 102:05
Budget Constraints - 202:43
Budget Constraints - 303:28
Hard Kernel Matrices: Kd,m04:33
Absolute Loss, no strong convexity05:11
Proof Idea - 106:21
Proof Idea - 206:36
Proof Idea - 306:40
Proof Idea - 406:53
Proof Idea - 507:00
Soft Regularization, General Losses - 108:09
Soft Regularization, General Losses - 208:26
Some Corollaries09:21
Low Rank10:45
Summary11:44
Thanks!13:06