Continuous Relaxations for Discrete Hamiltonian Monte Carlo thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Continuous Relaxations for Discrete Hamiltonian Monte Carlo

Published on Jan 14, 20132980 Views

Continuous relaxations play an important role in discrete optimization, but have not seen much use in approximate probabilistic inference. Here we show that a general form of the Gaussian Integral Tri

Related categories

Chapter list

Continuous Relaxations for Discrete Hamiltonian Monte Carlo00:00
The Gaussian Integral Trick00:46
The Convexity of Continuous Marginal02:17
Results on Node Marginal Estimation on Synthetic MRFs03:13