Thermal Robustness of Retrieval in Dense Associative Memories: LSE vs LSR Kernels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Petrova, Tatiana
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912965738889216
author Petrova, Tatiana
author_facet Petrova, Tatiana
contents Understanding whether retrieval in dense associative memories survives thermal noise is essential for bridging zero-temperature capacity proofs with the finite-temperature conditions of practical inference and biological computation. We use Monte Carlo simulations to map the retrieval phase boundary of two continuous dense associative memories (DAMs) on the $N$-sphere with an exponential number of stored patterns $M = e^{αN}$: a log-sum-exp (LSE) kernel and a log-sum-ReLU (LSR) kernel. Both kernels share the zero-temperature critical load $α_c(0)=0.5$, but their finite-temperature behavior differs markedly. The LSE kernel sustains retrieval at arbitrarily high temperatures for sufficiently low load, whereas the LSR kernel exhibits a finite support threshold below which retrieval is perfect at any temperature; for typical sharpness values this threshold approaches $α_c$, making retrieval nearly perfect across the entire load range. We also compare the measured equilibrium alignment with analytical Boltzmann predictions within the retrieval basin.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13350
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Thermal Robustness of Retrieval in Dense Associative Memories: LSE vs LSR Kernels
Petrova, Tatiana
Machine Learning
Disordered Systems and Neural Networks
Neural and Evolutionary Computing
Understanding whether retrieval in dense associative memories survives thermal noise is essential for bridging zero-temperature capacity proofs with the finite-temperature conditions of practical inference and biological computation. We use Monte Carlo simulations to map the retrieval phase boundary of two continuous dense associative memories (DAMs) on the $N$-sphere with an exponential number of stored patterns $M = e^{αN}$: a log-sum-exp (LSE) kernel and a log-sum-ReLU (LSR) kernel. Both kernels share the zero-temperature critical load $α_c(0)=0.5$, but their finite-temperature behavior differs markedly. The LSE kernel sustains retrieval at arbitrarily high temperatures for sufficiently low load, whereas the LSR kernel exhibits a finite support threshold below which retrieval is perfect at any temperature; for typical sharpness values this threshold approaches $α_c$, making retrieval nearly perfect across the entire load range. We also compare the measured equilibrium alignment with analytical Boltzmann predictions within the retrieval basin.
title Thermal Robustness of Retrieval in Dense Associative Memories: LSE vs LSR Kernels
topic Machine Learning
Disordered Systems and Neural Networks
Neural and Evolutionary Computing
url https://arxiv.org/abs/2603.13350