Scaling Laws for Associative Memories
Machine Learning
2024-02-22 v2 Artificial Intelligence
Computation and Language
Machine Learning
Neural and Evolutionary Computing
Abstract
Learning arguably involves the discovery and memorization of abstract rules. The aim of this paper is to study associative memory mechanisms. Our model is based on high-dimensional matrices consisting of outer products of embeddings, which relates to the inner layers of transformer language models. We derive precise scaling laws with respect to sample size and parameter size, and discuss the statistical efficiency of different estimators, including optimization-based algorithms. We provide extensive numerical experiments to validate and interpret theoretical results, including fine-grained visualizations of the stored memory associations.
Cite
@article{arxiv.2310.02984,
title = {Scaling Laws for Associative Memories},
author = {Vivien Cabannes and Elvis Dohmatob and Alberto Bietti},
journal= {arXiv preprint arXiv:2310.02984},
year = {2024}
}