Pith. sign in

REVIEW 2 cited by

Funnels: Exact maximum likelihood with dimensionality reduction

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 2112.08069 v1 pith:D5EMKW3P submitted 2021-12-15 cs.LG stat.ML

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

Normalizing flows are diffeomorphic, typically dimension-preserving, models trained using the likelihood of the model. We use the SurVAE framework to construct dimension reducing surjective flows via a new layer, known as the funnel. We demonstrate its efficacy on a variety of datasets, and show it improves upon or matches the performance of existing flows while having a reduced latent space size. The funnel layer can be constructed from a wide range of transformations including restricted convolution and feed forward layers.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Generative AI-enhanced Probabilistic Multi-Fidelity Surrogate Modeling Via Transfer Learning

    cs.LG 2026-01 conditional novelty 5.0 of 10

    A surjective normalizing flow, pretrained on low-fidelity data and fine-tuned on high-fidelity data, produces probabilistic structural-response surrogates that match high-fidelity accuracy with far fewer high-fidelity...

  2. Simultaneous Latent State Estimation and Latent Linear Dynamics Discovery from Image Observations

    cs.LG 2025-01 reject novelty 4.0 of 10

    The paper sketches NFPF, a normalizing-flow particle filter with jointly learned linear latent dynamics, but provides only qualitative and self-admittedly insufficient CartPole experiments.

Pith tools