Dense associative memory retrieval converges geometrically with O(log N) time and tolerates adversarial corruptions under separation and bounded-interference conditions, achieving capacity scaling Θ(N^{n-1}).
On the role of hidden states of modern hopfield network in transformer.arXiv preprint arXiv:2511.20698
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Algorithmic Analysis of Dense Associative Memory: Finite-Size Guarantees and Adversarial Robustness
Dense associative memory retrieval converges geometrically with O(log N) time and tolerates adversarial corruptions under separation and bounded-interference conditions, achieving capacity scaling Θ(N^{n-1}).