Efficient Online Learning via Randomized Rounding thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Efficient Online Learning via Randomized Rounding

Published on Jan 25, 20123461 Views

Most online algorithms used in machine learning today are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approa

Related categories

Chapter list

Efficient Online Learning via Randomized Rounding00:00
Online Learning00:02
An Inconvenient Truth01:01
This Paper02:08
Starting Point: Prediction of Binary Sequences03:23
Prediction of Binary Sequences - 104:23
Prediction of Binary Sequences - 206:28
Prediction of Binary Sequences - 307:01
The R² Forecaster - 107:48
The R² Forecaster - 208:48
The R² Forecaster - Analysis09:44
Application 1: Transductive Online Learning10:34
Application 2: Collaborative Filtering - 111:49
Application 2: Collaborative Filtering - 212:51
Application 2: Collaborative Filtering - 313:32
Conclusions14:57