Pith. sign in

REVIEW 7 cited by

On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.06578 v3 pith:CDEWRWDB submitted 2024-02-09 cs.LG stat.ML

classification cs.LGstat.ML
keywords flowsnormalizingunderstandingvolume-preservingcoupling-basedexpressivegeneralresults
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MIMFlow uses a VAE on masked images to feed semantic latents to a normalizing flow while a decoder handles high-frequency details, reporting FID 2.50 and 71.3% linear probing on ImageNet 256x256 with 128 tokens.

  2. Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows

    q-bio.NC 2025-06 conditional novelty 6.0 of 10

    A normalizing flow with a mixture-of-Gaussians latent space and a quadratic post-hoc approximation yields higher-order correlations and curvature estimates for neural manifolds in macaque visual cortex.

  3. Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows

    stat.ML 2025-05 conditional novelty 6.0 of 10

    A conditional normalizing flow method that solves the primal optimal transport problem and computes Wasserstein-2 barycenters as weighted averages of maps from a shared latent distribution.

  4. Expert-elicitation method for non-parametric joint priors using normalizing flows

    stat.ME 2024-11 conditional novelty 6.0 of 10

    A normalizing-flow-based method learns non-parametric joint prior distributions for Bayesian models by matching simulated predictions to expert-elicited statistics.

  5. Neural Conjugate Flows: Physics-informed architectures with flow structure

    cs.LG 2024-11 conditional novelty 6.0 of 10

    Neural Conjugate Flows represent ODE solutions as a learned coordinate change followed by an affine flow, giving exact group structure and a universal approximation claim.

  6. Normalizing Flows are Capable Models for Continuous Control

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A simple normalizing flow policy matches or outperforms diffusion and autoregressive baselines across imitation learning, offline RL, goal-conditioned RL, and unsupervised RL on 82 tasks.

  7. Causally Consistent Normalizing Flow

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A normalizing flow that preserves causal structure by transforming variables in topological batches, enabling deep causally consistent generative models.

Pith tools