Bootstrap Your Flow

Abstract

Normalizing flows are flexible, parameterized distributions that can be used to approximate expectations from intractable distributions via importance sampling. However, current flow-based approaches are limited on challenging targets where they either suffer from mode seeking behaviour or high variance in the training loss, or rely on samples from the target distribution, which may not be available. To address these challenges, we combine flows with annealed importance sampling (AIS), while using the $\alpha$-divergence as our objective, in a novel training procedure, FAB (Flow AIS Bootstrap). Thereby, the flow and AIS improve each other in a bootstrapping manner. We demonstrate that FAB can be used to produce accurate approximations to complex target distributions, including Boltzmann distributions, in problems where previous flow-based methods fail.

References in corpus (7)

• Variational Inference with Normalizing Flows
• Density estimation using Real NVP
• Residual Flows for Invertible Generative Modeling
• SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
• Learning Deep Generative Models with Annealed Importance Sampling
• Smooth Normalizing Flows
• Resampling Base Distributions of Normalizing Flows