Pith. sign in

REVIEW 1 cited by

Why Unsupervised Deep Networks Generalize

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 2012.03531 v1 pith:URINQU2E submitted 2020-12-07 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords deeplearningnetworkparameterssuggestestimatesgeneralizationgroup
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very few parameters, despite the fact that naive estimates suggest otherwise. Our central hypothesis is that the mechanisms behind the renormalization group are also at work in deep learning, and that this leads to a resolution of the generalization puzzle. We show detailed quantitative evidence that proves the hypothesis for an RBM, by showing that the trained RBM is discarding high momentum modes. Specializing attention mainly to autoencoders, we give an algorithm to determine the network's parameters directly from the learning data set. The resulting autoencoder almost performs as well as one trained by deep learning, and it provides an excellent initial condition for training, reducing training times by a factor between 4 and 100 for the experiments we considered. Further, we are able to suggest a simple criterion to decide if a given problem can or can not be solved using a deep network.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. A Two-Phase Perspective on Deep Learning Dynamics

    hep-th 2025-04 conditional novelty 4.0 of 10

    Learning in deep networks is proposed to consist of a fast memorization phase followed by a slow compression phase that drives generalization, with mutual information between hidden layers and inputs as a progress measure.

Pith tools