Pith. sign in

REVIEW 6 cited by

Binary perceptrons capacity via fully lifted random duality theory

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 2312.00073 v1 pith:YOZN2H6F submitted 2023-11-29 math.PR cond-mat.dis-nncs.ITmath.ITmath.STstat.MLstat.TH

classification math.PRcond-mat.dis-nncs.ITmath.ITmath.STstat.MLstat.TH
keywords capacityemphfullyobtainedperceptronsrandombinarycite
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We study the statistical capacity of the classical binary perceptrons with general thresholds $\kappa$. After recognizing the connection between the capacity and the bilinearly indexed (bli) random processes, we utilize a recent progress in studying such processes to characterize the capacity. In particular, we rely on \emph{fully lifted} random duality theory (fl RDT) established in \cite{Stojnicflrdt23} to create a general framework for studying the perceptrons' capacities. Successful underlying numerical evaluations are required for the framework (and ultimately the entire fl RDT machinery) to become fully practically operational. We present results obtained in that directions and uncover that the capacity characterizations are achieved on the second (first non-trivial) level of \emph{stationarized} full lifting. The obtained results \emph{exactly} match the replica symmetry breaking predictions obtained through statistical physics replica methods in \cite{KraMez89}. Most notably, for the famous zero-threshold scenario, $\kappa=0$, we uncover the well known $\alpha\approx0.8330786$ scaled capacity.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. CLuP practically achieves $\sim 1.77$ positive and $\sim 0.33$ negative Hopfield model ground state free energy

    cond-mat.dis-nn 2025-07 conditional novelty 6.0 of 10

    CLuP±Hop approximates Hopfield ground state free energies to within about 0.3% using simple gradient descent, backed by the author's fully lifted random duality theory.

  2. Deep ReLU networks -- injectivity capacity upper bounds

    stat.ML 2024-12 reject novelty 6.0 of 10

    For deep ReLU networks with random Gaussian weights, the paper gives upper bounds on the layer expansion needed for injectivity and finds the expansion need saturates by four layers.

  3. A CLuP algorithm to practically achieve $\sim 0.76$ SK--model ground state free energy

    cond-mat.dis-nn 2025-07 conditional novelty 5.0 of 10

    The authors propose a CLuP-SK barrier-descent algorithm and report it achieves approximately 0.76 of the SK ground state free energy for n around 2000 to 8000, approaching the theoretical Parisi limit of about 0.763.

  4. Rare dense solutions clusters in asymmetric binary perceptrons -- local entropy via fully lifted RDT

    stat.ML 2025-06 conditional novelty 5.0 of 10

    For the asymmetric binary perceptron, the worst-case local entropy breaks down for constraint density alpha in (0.77, 0.78), matching replica predictions and the range where fast algorithms stop working.

  5. Fully lifted \emph{blirp} interpolation -- a large deviation view

    math.PR 2025-06 conditional novelty 5.0 of 10

    A large-deviation upgrade of fully lifted blirp interpolation is derived, yielding explicit derivative identities that the author links to local entropy and computational gaps in perceptron models.

  6. A large deviation view of \emph{stationarized} fully lifted blirp interpolation

    math.PR 2025-06 conditional novelty 4.0 of 10

    The paper derives new derivative identities for a stationarized fully lifted bilinearly indexed random process interpolator and states an equality between large deviation limits at the opposite ends of an interpolation path.

Pith tools