Sign up Sign in
video thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

MCMC Learning

Published on 2015-08-202064 Views

Varun Kanade

The theory of learning under the uniform distribution is rich and deep, with connections to cryptography, computational complexity, and the analysis of boolean functions to name a few areas. This theo

COLT 2015 - Paris

Related categories

Active LearningComputational Learning TheoryReinforcement LearningSemi-supervised LearningOn-line Learning

Presentation

MCMC Learning00:00
PAC Learning00:06
Agnostic Learning01:02
Challenge01:59
Uniform Distribution Learning02:26
But ...04:12
Markov Random Fields - 104:44
Markov Random Fields - 205:36
Learning Model (PAC/Agnostic)06:28
Gibbs Sampling (MCMC Algorithm)07:09
Ising Model07:41
Harmonic Analysis Using Eigenvectors - 108:40
Harmonic Analysis Using Eigenvectors - 209:43
Power Iteration to Find Eigenvectors - 110:13
Power Iteration to Find Eigenvectors - 211:25
When can we do this?12:18
Discrete Spectrum13:24
Learning Algorithm13:59
Main Results15:26
Open Questions17:00