Pith. sign in

REVIEW 4 cited by

Scaling Laws for Associative Memories

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.02984 v2 pith:RG6K2SBI submitted 2023-10-04 stat.ML cs.AIcs.CLcs.LGcs.NE

classification stat.MLcs.AIcs.CLcs.LGcs.NE
keywords associativeincludinglawsmemoryscalingsizeabstractalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Muon in Associative Memory Learning: Training Dynamics and Scaling Laws

    cs.LG 2026-02 conditional novelty 6.0 of 10

    In a linear softmax memory model, Muon equalizes learning across frequency tiers and gives exponential (noiseless) or T^{-2} (noisy power-law) convergence, versus polynomial or T^{-(1-1/β)} for gradient descent.

  2. From Zipf's Law to Neural Scaling through Heaps' Law and Hilberg's Hypothesis

    cs.IT 2025-12 conditional novelty 6.0 of 10

    Zipf's law, via differential Heaps and Hilberg laws, forces a power-law lower bound on the excess cross entropy of any entropy-bounded foundation model.

  3. Extending LLM Context via Associative Recurrent Memory

    cs.CL 2026-07 conditional novelty 5.0 of 10

    ARMT-augmented 1B-class LLMs, trained with continued pretraining, synthetic long data, curriculum, and selective memory layers, keep in-window quality while generalizing past 32k–65k tokens at constant memory and ~30%...

  4. The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations

    cs.LG 2025-07 conditional novelty 5.0 of 10

    FACT is a first-order stationarity identity for weight matrices that matches or beats the Neural Feature Ansatz as a description of learned features at convergence.

Pith tools