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

arXiv: https://arxiv.org/abs/2603.13350 · HTML: https://mlsanity.com/paper/2603.13350/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 9 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Builds on (most cited first, 1 of 1)

- [Dense Associative Memory with Epanechnikov Energy](https://mlsanity.com/paper/2506.10801/) (2025)

## Abstract (arXiv)

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 = eα N: a log-sum-exp (LSE) kernel and a log-sum-ReLU (LSR) kernel. Both kernels share the zero-temperature critical load αc(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 αc, making retrieval nearly perfect across the entire load range. We also compare the measured equilibrium alignment with analytical Boltzmann predictions within the retrieval basin.