Batch and match: black-box variational inference with a score-based divergence

arXiv:2402.14758v1 Announce Type: cross
Abstract: Most leading implementations of black-box variational inference (BBVI) are based on optimizing a stochastic evidence lower bound (ELBO). But such approaches to BBVI often converge slowly due to the high variance of their gradient estimates. In this work, we propose batch and match (BaM), an alternative approach to BBVI based on a score-based divergence. Notably, this score-based divergence can be optimized by a closed-form proximal update for Gaussian variational families with full covariance matrices. We …

abstract arxiv box converge cs.ai cs.lg divergence evidence gradient inference match stat.co stat.ml stochastic type variance work