Our paper "Batch, match, and patch: low-rank approximations for score-based variational inference" is accepted to
#AISTATS2025.
This paper addresses score-based variational inference with Gaussians (batch and match VI) with low rank + diagonal covariances.
Preprint:
arxiv.org/abs/2410.22292
Batch, match, and patch: low-rank approximations for score-based variational inference
Black-box variational inference (BBVI) scales poorly to high dimensional problems when it is used to estimate a multivariate Gaussian approximation with a full covariance matrix. In this paper, we ext...
Going to my first ever AISTATS and first time in Thailand! 🎉🌴🍾
