Pith. sign in

REVIEW 4 cited by

Input complexity and out-of-distribution detection with likelihood-based generative models

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 1909.11480 v3 pith:XWW5LM7M submitted 2019-09-25 cs.LG stat.ML

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

Likelihood-based generative models are a promising resource to detect out-of-distribution (OOD) inputs which could compromise the robustness or reliability of a machine learning system. However, likelihoods derived from such models have been shown to be problematic for detecting certain types of inputs that significantly differ from training data. In this paper, we pose that this problem is due to the excessive influence that input complexity has in generative models' likelihoods. We report a set of experiments supporting this hypothesis, and use an estimate of input complexity to derive an efficient and parameter-free OOD score, which can be seen as a likelihood-ratio, akin to Bayesian model comparison. We find such score to perform comparably to, or even better than, existing OOD detection approaches under a wide range of data sets, models, model sizes, and complexity estimates.

Discussion (0). Sign in 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. Generalization and Memorization in Rectified Flow

    cs.LG 2026-03 accept novelty 7.0 of 10

    Rectified Flow models peak in membership-inference vulnerability at the flow midpoint under uniform training; U-shaped timestep sampling suppresses memorization without harming FID.

  2. Native Extrapolation Awareness in Flow-Based Conditional Generation

    cs.LG 2026-02 conditional novelty 6.0 of 10

    A contrastive flow-matching objective makes off-manifold conditions produce curved trajectories, so path curvature (the DOT score) separates invalid from valid inputs.

  3. Energy-Based Transformers are Scalable Learners and Thinkers

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Energy-Based Transformers learn to predict by gradient-descent minimization of a learned energy function, and the paper reports faster pretraining scaling and inference-time thinking gains over Transformer++ and Diffu...

  4. 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.

Pith tools