Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval

TL;DR

This paper investigates the capacity of linear associative memories under different retrieval criteria, revealing phase transitions and thresholds for winner-take-all and listwise retrieval regimes.

Contribution

It introduces a formal framework for understanding capacity thresholds in linear memory models, including a new listwise retrieval criterion and an asymptotic theory for its performance.

Findings

Top-1 retrieval requires $d^2 \\sim n \\log n$ scale.

Listwise retrieval capacity scales quadratically as $d^2 \\sim n$.

A conjectural sharp top-1 threshold is $d^2 \\sim 2n \\log n$.

Abstract

How many key-value associations can a $d\times d$ linear memory store? We show that the answer depends not only on the $d^2$ degrees of freedom in the memory matrix, but also on the retrieval criterion. In an isotropic Gaussian model for the stored pairs, we show that top-1 retrieval, where every signal must beat its largest distractor, requires the logarithmic model-size scale $d^2\asymp n\log n$. We prove that the correlation matrix memory construction, which stores associations by superposing key-target outer products, achieves this scale through a sharp phase transition, and that the same scaling is necessary for any linear memory. Thus the logarithm is the intrinsic extreme-value price of winner-take-all decoding. We next consider listwise retrieval, where the correct target need not be the unique top-scoring item but should remain among the strongest candidates. To formalize this regime, we propose the Tail-Average Margin (TAM), a convex upper-tail criterion that certifies inclusion of the correct target in a controlled candidate list. Under this listwise retrieval criterion, the capacity follows the quadratic scale $d^2\asymp n$. At load $n/d^2\to\alpha$, we develop an exact asymptotic theory for the TAM empirical-risk minimizer through a two-parameter scalar variational principle. The theory has a rich phenomenology: in the ridgeless limit it yields a closed-form critical load separating satisfiable and unsatisfiable phases, and it predicts the limiting laws of true scores, competitor scores, margins, and percentile profiles. Finally, a small-tail extrapolation further leads to the conjectural sharp top-1 threshold $d^2\sim 2n\log n$.