On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “Thouless-Anderson-Palmer”

Training Restricted Boltzmann Machines via the Thouless-Anderson-Palmer Free Energycond-mat.dis-nn

New method improves training of Boltzmann machines using Thouless-Anderson-Palmer approach.

problem Training efficient Boltzmann machines with hidden units.

method Deterministic iterative procedure based on Thouless-Anderson-Palmer approach.

result Performance equal to, and sometimes superior to, contrastive divergence.

Boltzmann machines Thouless-Anderson-Palmer training algorithms statistical physics

2015-06-09abs ↗pdf ↗

Effective Mean-Field Inference Method for Nonnegative Boltzmann Machinesstat.ML

Paper proposes an effective mean-field inference method for NNBMs.

problem Inference in NNBMs is challenging due to their complex structure.

method Uses mean-field method and diagonal consistency method.

result Effective inference method for NNBMs is proposed.

mean-field method Thouless--Anderson--Palmer equation nonnegative Boltzmann machines diagonal consistency method

2016-03-08abs ↗pdf ↗

Susceptibility Propagation by Using Diagonal Consistencycond-mat.stat-mech

Improved susceptibility propagation for Markov random fields using diagonal matching.

problem Approximate computation of Markov random fields with robustness across network structures.

method Combines belief propagation and linear response method with diagonal matching for inverse Ising problems.

result Proposed method reduces to standard susceptibility propagation and Thouless-Anderson-Palmer equation in specific cases.

susceptibility propagation Markov random fields diagonal matching inverse Ising problems robustness

2017-12-01abs ↗pdf ↗

The TAP free energy for high-dimensional linear regressionmath.PR

Derives TAP approximation for Bayesian linear regression.

problem Log-normalizing constant of posterior distribution in high-dimensional linear regression.

method Variational representation and Thouless-Anderson-Palmer approximation.

result Proves TAP approximation for spherical prior in proportional asymptotic regime.

Bayesian linear regression log-normalizing constant TAP approximation spin glass theory spherical prior

2022-03-14abs ↗pdf ↗

A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machinescs.LG

A new framework trains RBMs deterministically for unsupervised learning.

problem Training and evaluation of RBMs with weak interactions.

method TAP mean-field approximation for generalized latent-variable models.

result Effective deterministic training and interesting unsupervised learning features demonstrated.

Restricted Boltzmann Machines TAP approximation Unsupervised Learning Deterministic Training Mean-Field Theory

2017-02-10abs ↗pdf ↗

Bayes-optimal limits in structured PCA, and how to reach themcs.IT

Bayes-optimal limits in PCA with structured noise are determined.

problem Analyzing statistical dependencies in measurement noise for high-dimensional inference.

method Study of spiked matrix model with low-order polynomial orthogonal noise, providing Bayes-optimal limits and proposing a novel AMP.

result A novel AMP algorithm reaches the information-theoretic limits for more general priors.

PCA Bayes-optimal limits Structured noise AMP Replica method

2022-10-03abs ↗pdf ↗

Weighted Community Detection and Data Clustering Using Message Passingphysics.soc-ph

New method clusters weighted networks and data with high accuracy.

problem Clustering weighted and directed networks with varying weights.

method Extends message passing algorithms to Potts model at critical temperature, solving marginals using belief propagation.

result Significantly outperforms existing algorithms in community detection and clustering tasks.

community detection message passing clustering statistical physics belief propagation

2018-01-30abs ↗pdf ↗