Pith. sign in

REVIEW 4 cited by

A Review of Change of Variable Formulas for Generative Modeling

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 2308.02652 v1 pith:KBYJVFDI submitted 2023-08-04 cs.LG

classification cs.LG
keywords formulasmodelallowalwaysarchitecturesbayesianbeenchange
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Change-of-variables (CoV) formulas allow to reduce complicated probability densities to simpler ones by a learned transformation with tractable Jacobian determinant. They are thus powerful tools for maximum-likelihood learning, Bayesian inference, outlier detection, model selection, etc. CoV formulas have been derived for a large variety of model types, but this information is scattered over many separate works. We present a systematic treatment from the unifying perspective of encoder/decoder architectures, which collects 28 CoV formulas in a single place, reveals interesting relationships between seemingly diverse methods, emphasizes important distinctions that are not always clear in the literature, and identifies surprising gaps for future research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. NAE: Normalizing AutoEncoder

    cs.LG 2026-08 conditional novelty 6.0 of 10

    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 da...

  2. Mitigating Diffusion Model Hallucinations with Dynamic Guidance

    cs.CV 2025-10 conditional novelty 6.0 of 10

    Dynamic per-step selection of the classifier-guidance target reduces diffusion-model hallucinations on 2D, shape, and hand-image benchmarks, with proxy-metric gains on ImageNet.

  3. Time-dependent density estimation using binary classifiers

    stat.ML 2025-06 conditional novelty 6.0 of 10

    A time-dependent classifier whose pre-activation approximates the partial time derivative of the log-density makes fully data-driven, path-independent evaluation of evolving probability densities possible.

  4. Super-Resolving Normalising Flows for Lattice Field Theories

    hep-lat 2024-12 conditional novelty 6.0 of 10

    An RG-inspired normalising flow with exact likelihood tracking samples 2D phi^4 theory on 128x128 lattices using only 4x4 MCMC samples, keeping high ESS/N in symmetric and broken phases.

Pith tools