LGMLJul 15, 2021

On the expressivity of bi-Lipschitz normalizing flows

arXiv:2107.07232v319 citations
AI Analysis

This addresses a fundamental limitation in generative modeling for researchers and practitioners using normalizing flows, though it is incremental in analyzing existing constraints.

The paper tackles the problem of limited expressivity in bi-Lipschitz normalizing flows, showing that they struggle to approximate certain target distributions, with lower bounds on total variation distance provided as evidence.

An invertible function is bi-Lipschitz if both the function and its inverse have bounded Lipschitz constants. Nowadays, most Normalizing Flows are bi-Lipschitz by design or by training to limit numerical errors (among other things). In this paper, we discuss the expressivity of bi-Lipschitz Normalizing Flows and identify several target distributions that are difficult to approximate using such models. Then, we characterize the expressivity of bi-Lipschitz Normalizing Flows by giving several lower bounds on the Total Variation distance between these particularly unfavorable distributions and their best possible approximation. Finally, we discuss potential remedies which include using more complex latent distributions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes