On the Universality of Coupling-based Normalizing Flows
We present a novel theoretical framework for understanding the expressive power of normalizing flows. Despite their prevalence in scientific applications, a comprehensive understanding of flows remains elusive due to their restricted architectures. Existing theorems fall short as they require the us...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We present a novel theoretical framework for understanding the expressive
power of normalizing flows. Despite their prevalence in scientific
applications, a comprehensive understanding of flows remains elusive due to
their restricted architectures. Existing theorems fall short as they require
the use of arbitrarily ill-conditioned neural networks, limiting practical
applicability. We propose a distributional universality theorem for
well-conditioned coupling-based normalizing flows such as RealNVP. In addition,
we show that volume-preserving normalizing flows are not universal, what
distribution they learn instead, and how to fix their expressivity. Our results
support the general wisdom that affine and related couplings are expressive and
in general outperform volume-preserving flows, bridging a gap between empirical
results and theoretical understanding. |
---|---|
DOI: | 10.48550/arxiv.2402.06578 |