AI RESEARCH
Thermal Robustness of Retrieval in Dense Associative Memories: LSE vs LSR Kernels
arXiv CS.LG
•
ArXi:2603.13350v1 Announce Type: new 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 d patterns $M = e^{\alpha N}$: a log-sum-exp (LSE) kernel and a log-sum-ReLU (LSR) kernel.