Dense Associative Memory with Epanechnikov Energy

NeurIPSSpotlight2025

Authors: Benjamin Hoover, Zhaoyang Shi, Krishna Balasubramanian, Dmitry Krotov, Parikshit Ram
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

We propose a novel energy function for Dense Associative Memory (DenseAM) networks, the log-sum-ReLU (LSR), inspired by optimal kernel density estimation…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

kernel memory

← All NeurIPS 2025 Spotlight papers · Browse the whole archive