A conditional surrogate loss that always picks the gradient estimate aligned with the reconstruction loss improves flow autoencoder training and reaches state-of-the-art generative performance on molecules, tabular data, and images.
Bootstrap Your Flow
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NAE: Normalizing AutoEncoder
A conditional surrogate loss that always picks the gradient estimate aligned with the reconstruction loss improves flow autoencoder training and reaches state-of-the-art generative performance on molecules, tabular data, and images.