Concepts2
📚TheoryAdvanced
PAC-Bayes Theory
PAC-Bayes provides high-probability generalization bounds for randomized predictors by comparing a data-dependent posterior Q to a fixed, data-independent prior P through KL(Q||P).
#pac-bayes#generalization bound#kl divergence+12
📚TheoryIntermediate
ELBO (Evidence Lower Bound)
The Evidence Lower Bound (ELBO) is a tractable lower bound on the log evidence log p(x) that enables learning and inference in latent variable models like VAEs.
#elbo#variational inference#vae+12