Energy-based models.
December 10, 2020 — November 11, 2021
approximation
Bayes
generative
likelihood free
Monte Carlo
neural nets
optimization
probabilistic algorithms
probability
statistics
unsupervised
Is there anything here? I have been given a few different explanations as to what EBMs are. From the outside, it looks like something about probabilistic NNs but using various tricks to avoid normalising.
That could describe posterior MCMC, of course, so I reckon there must be something extra here?
1 References
LeCun, Chopra, Hadsell, et al. 2006. “A Tutorial on Energy-Based Learning.” In Predicting Structured Data.
Parshakova, Andreoli, and Dymetman. 2019. “Distributional Reinforcement Learning for Energy-Based Sequential Models.”
Schröder, Ou, Lim, et al. 2023. “Energy Discrepancies: A Score-Independent Loss for Energy-Based Models.”