Pith. sign in

REVIEW 4 cited by

Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality

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 1906.02994 v2 pith:O2S4JVHL submitted 2019-06-07 stat.ML cs.LG

Eric Nalisnick , Akihiro Matsukawa , Yee Whye Teh , Balaji Lakshminarayanan This is my paper · ORCID
classification stat.MLcs.LG
keywords inputsmodelout-of-distributiondatadeepgenerativelikelihoodmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is caused by a mismatch between the model's typical set and its areas of high probability density. In-distribution inputs should reside in the former but not necessarily in the latter, as previous work has presumed. To determine whether or not inputs reside in the typical set, we propose a statistically principled, easy-to-implement test using the empirical distribution of model likelihoods. The test is model agnostic and widely applicable, only requiring that the likelihood can be computed or closely approximated. We report experiments showing that our procedure can successfully detect the out-of-distribution sets in several of the challenging cases reported by Nalisnick et al. (2019).

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. OpenAlex reports about 59 citations worldwide. Full citation record

  1. Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics

    cs.CL 2026-06 conditional novelty 7.0 of 10

    Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank the...

  2. Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps

    cs.LG 2025-01 reject novelty 7.0 of 10

    A volume-preserving reparameterization makes the likelihood of cascaded diffusion models exactly computable, giving state-of-the-art density estimation on standard image benchmarks.

  3. OOD Detection with immature Models

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Partially trained GLOW models match or outperform fully trained models for out-of-distribution image detection when scored by layer-wise gradient norms.

  4. Zero-Shot Image Anomaly Detection Using Generative Foundation Models

    cs.CV 2025-07 conditional novelty 4.0 of 10

    DiffPathV2 detects out-of-distribution images by measuring weighted errors in a pretrained diffusion model's predicted noise, without retraining on the target dataset.

Pith tools