Dimension-Free Exponentiated Gradient thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Dimension-Free Exponentiated Gradient

Published on Nov 07, 20141724 Views

We present a new online learning algorithm that extends the exponentiated gradient to infinite dimensional spaces. Our analysis shows that the algorithm is implicitly able to estimate the L2 norm of t

Related categories

Chapter list

Dimension-Free Exponentiated Gradient a.k.a. Gradient Descent without any Parameter00:00
Uncostrained Online Learning with Lipschitz Loss01:16
An Improved Lower Bound02:13
Dimension-Free Exponentiated Gradient02:42