TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Implicit Generation and Generalization Methods for Energy-Based Models

10 pointsby gdbabout 6 years ago

1 comment

lenticularabout 6 years ago
I&#x27;m not really clear on the difference between Bayesian methods and EBMs. EBMs associate an &quot;energy&quot; to each point the the parameter space, but this energy is just the log-partition function of some distribution. Sampling schemes for such models are just MCMC methods, which are already a long-established genre of Bayesian techniques.<p>The article talks about sampling from EBMs using Langevin Dynamics, but it appears to be identical to Bayesian sampling with Langevin dynamics, which has been fairly popular for a few years. Some of the other stuff is just focused on minimizing the EBM, but then that&#x27;s just identical to MAP&#x2F;frequentist estimates.<p>Also, they gloss over a lot of problems that Langevin dynamics has. Unlike what they claim, it is not at all good at finding nodes separated by low-probability regions, since it has to take increasingly small steps to maintain asymtotic correctness.
评论 #19455197 未加载