Pith. sign in

REVIEW 10 cited by

Improving Variational Inference with Inverse Autoregressive Flow

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1606.04934 v2 pith:BK5Q2CUZ submitted 2016-06-15 cs.LG stat.ML

Diederik P. Kingma , Tim Salimans , Rafal Jozefowicz , Xi Chen , Ilya Sutskever , Max Welling This is my paper · ORCID
classification cs.LGstat.ML
keywords autoregressiveflowvariationalflowsinferenceinverselatentneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed flow consists of a chain of invertible transformations, where each transformation is based on an autoregressive neural network. In experiments, we show that IAF significantly improves upon diagonal Gaussian approximate posteriors. In addition, we demonstrate that a novel type of variational autoencoder, coupled with IAF, is competitive with neural autoregressive models in terms of attained log-likelihood on natural images, while allowing significantly faster synthesis.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 186 citations worldwide. Full citation record

  1. Machine-learning techniques for model-independent searches in dijet final states

    hep-ex 2025-12 accept novelty 7.0 of 10

    Five ML anomaly-detection methods enhance model-agnostic dijet searches at CMS, and a weakly supervised tagger identifies hadronic top-quark decays in data nearly as well as a supervised classifier.

  2. Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    PRIOR replaces masking-based ordering pressure with predictive residual inference using level-wise predictors to produce well-ordered representations that maintain or improve performance across budgets, especially in ...

  3. Analytic Bijections for Smooth and Interpretable Normalizing Flows

    cs.LG 2026-01 conditional novelty 6.0 of 10

    Three new analytic bijections and a radial flow architecture give globally smooth, closed-form invertible normalizing flows that match or beat spline baselines on benchmarks and improve phi^4 lattice-field sampling.

  4. Trends in the Population of Binary Black Holes Following the Fourth Gravitational-Wave Transient Catalog: a Data-Driven Analysis

    astro-ph.HE 2025-09 conditional novelty 6.0 of 10

    A data-driven 'pi stroke' analysis of GWTC-4 reveals a secondary-black-hole mass gap at 38-120 solar masses, a possible chi1-chi2 spin correlation, and suggests the chi-eff-q anti-correlation may be a model artifact.

  5. Continuous Semi-Implicit Models

    stat.ML 2025-06 conditional novelty 6.0 of 10

    CoSIM extends hierarchical semi-implicit variational inference to continuous time, yielding a simulation-free, multistep consistency-style distillation of pretrained diffusion models.

  6. Machine Learning Assisted Parameter-Space Searches for Lensed Gravitational Waves

    gr-qc 2025-09 conditional novelty 5.0 of 10

    Normalizing flow based non-Gaussian consistency tests in a compressed detector basis select GW170104-GW170814 as the only promising lensed pair in GWTC-3.

  7. Bridging the inference gap in Mutimodal Variational Autoencoders

    cs.LG 2025-02 conditional novelty 5.0 of 10

    A two-stage multimodal VAE with normalizing-flow conditional encoders (plus a shared-projector variant) improves cross-modal generation coherence over mixture-of-experts baselines on four benchmarks.

  8. eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions

    stat.ML 2026-06 unverdicted novelty 4.0 of 10

    X-VAE uses empirical statistics from a pretrained autoencoder to set a data-adaptive Gaussian prior and introduces a latent scaling factor for controllable generation.

  9. Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection

    cs.LG 2025-06 conditional novelty 4.0 of 10

    A dataset-specific geometric split of latent dimensions across HVAE layers improves OOD detection over fixed baseline configurations.

  10. Hierarchical Sequence to Sequence Voice Conversion with Limited Data

    eess.AS 2019-07 unverdicted novelty 4.0 of 10

    Hierarchical seq2seq model for parallel voice conversion pretrained as autoencoder on single-speaker data then adapted to limited multispeaker data, using mel spectrograms converted via wavenet vocoder.

Pith tools