Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures
Organizations: Departement d’Informatique, École Normale Supérieure, Université PSL, CNRS · Laboratoire de Physique de l’École Normale Supérieure, Université PSL, CNRS
Abstract
Mode collapse, the failure to capture one or more modes when targeting a multimodal distribution, is a central challenge in modern variational inference. In this work, we provide a mathematical analysis of annealing based strategies for mitigating mode collapse in a tractable setting: learning a Gaussian mixture, where mode collapse is known to arise. Leveraging a low dimensional summary statistics description, we precisely characterize the interplay between the initial temperature and the annealing rate, and derive a sharp formula for the probability of mode collapse. Our analysis shows that an appropriately chosen annealing scheme can robustly prevent mode collapse. Finally, we present numerical evidence that these theoretical tradeoffs qualitatively extend to neural network based models, RealNVP normalizing flows, providing guidance for designing annealing strategies mitigating mode collapse in practical variational inference pipelines.
Figures & tables
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
Variational Inference
Variational inference approximates complex Bayesian posteriors with tractable distributions that support faster inference and uncertainty estimates.
See all 161 papers