Training Energy-Based Normalizing Flow with Score-Matching Objectives

Chen-Hao Chao · Wei-Fang Sun · Yen-Chang Hsu · Zsolt Kira · Chun-Yi Lee

Great Hall & Hall B1+B2 (level 1) #614
[ ] [ Project Page ]
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST

Abstract: In this paper, we establish a connection between the parameterization of flow-based and energy-based generative models, and present a new flow-based modeling approach called energy-based normalizing flow (EBFlow). We demonstrate that by optimizing EBFlow with score-matching objectives, the computation of Jacobian determinants for linear transformations can be entirely bypassed. This feature enables the use of arbitrary linear layers in the construction of flow-based models without increasing the computational time complexity of each training iteration from $\mathcal{O}(D^2L)$ to $\mathcal{O}(D^3L)$ for an $L$-layered model that accepts $D$-dimensional inputs. This makes the training of EBFlow more efficient than the commonly-adopted maximum likelihood training method. In addition to the reduction in runtime, we enhance the training stability and empirical performance of EBFlow through a number of techniques developed based on our analysis of the score-matching methods. The experimental results demonstrate that our approach achieves a significant speedup compared to maximum likelihood estimation while outperforming prior methods with a noticeable margin in terms of negative log-likelihood (NLL).

Chat is not available.