English
Related papers

Related papers: Beyond Scaling Laws: Understanding Transformer Per…

200 papers

This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain $[0,1]^d$ and $d$-dimensional compact Riemannian manifolds. We propose a novel constructive approximation framework for…

Machine Learning · Statistics 2026-05-12 Zhongjie Shi , Wenjing Liao

This work focuses on the training dynamics of one associative memory module storing outer products of token embeddings. We reduce this problem to the study of a system of particles, which interact according to properties of the data…

Machine Learning · Computer Science 2024-03-01 Vivien Cabannes , Berfin Simsek , Alberto Bietti

Associative memory, a form of content-addressable memory, facilitates information storage and retrieval in many biological and physical systems. In statistical mechanics models, associative memory at equilibrium is represented through…

Disordered Systems and Neural Networks · Physics 2022-03-08 Agnish Kumar Behera , Madan Rao , Srikanth Sastry , Suriyanarayanan Vaikuntanathan

Dense Associative Memories or Modern Hopfield Networks have many appealing properties of associative memory. They can do pattern completion, store a large number of memories, and can be described using a recurrent neural network with a…

Neural and Evolutionary Computing · Computer Science 2021-07-29 Dmitry Krotov

Sequence models face a fundamental tradeoff between memory capacity and computational efficiency. Transformers achieve expressive context modeling at quadratic cost, while linear attention and state-space models run in linear time by…

Machine Learning · Computer Science 2026-05-11 Yaxita Amin , Helen Zichen Li , Mengfan Zhang , Samet Ayhan

Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that…

Machine Learning · Computer Science 2026-03-24 Tasmay Pankaj Tibrewal , Pritish Saha , Ankit Meda , Kunal Singh , Pradeep Moturi

The relationship between memorization and generalization in large language models (LLMs) remains an open area of research, with growing evidence that the two are deeply intertwined. In this work, we investigate this relationship by…

Machine Learning · Computer Science 2025-06-19 Joshua Barron , Devin White

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

When training deep neural networks, a model's generalization error is often observed to follow a power scaling law dependent both on the model size and the data size. Perhaps the best known example of such scaling laws are for…

Machine Learning · Computer Science 2024-11-12 Alex Havrilla , Wenjing Liao

We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small…

Machine Learning · Computer Science 2025-10-22 Brady Bhalla , Honglu Fan , Nancy Chen , Tony Yue YU

Associative memory models based on Hopfield networks and self-attention based on key-value mechanisms have been popular approaches in the study of memory mechanisms in deep learning. It has been pointed out that the state update rule of the…

Machine Learning · Computer Science 2025-11-27 Tsubasa Masumura , Masato Taki

Recent developments in large-scale machine learning suggest that by scaling up data, model size and training time properly, one might observe that improvements in pre-training would transfer favorably to most downstream tasks. In this work,…

Machine Learning · Computer Science 2021-10-06 Samira Abnar , Mostafa Dehghani , Behnam Neyshabur , Hanie Sedghi

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

We study empirical scaling laws for transfer learning between distributions in an unsupervised, fine-tuning setting. When we train increasingly large neural networks from-scratch on a fixed-size dataset, they eventually become data-limited…

Machine Learning · Computer Science 2021-02-03 Danny Hernandez , Jared Kaplan , Tom Henighan , Sam McCandlish

Hybrid sequence models--combining Transformer and state-space model layers--seek to gain the expressive versatility of attention as well as the computational efficiency of state-space model layers. Despite burgeoning interest in hybrid…

Machine Learning · Computer Science 2026-03-11 John Cooper , Ilias Diakonikolas , Mingchen Ma , Frederic Sala

Recent work on Transformer-based large language models (LLMs) has revealed striking limits in their working memory capacity, similar to what has been found in human behavioral studies. Specifically, these models' performance drops…

Computation and Language · Computer Science 2024-11-19 Dongyu Gong , Hantao Zhang

Energy-based probabilistic models learned by maximizing the likelihood of the data are limited by the intractability of the partition function. A widely used workaround is to maximize the pseudo-likelihood, which replaces the global…

Statistical Mechanics · Physics 2026-03-31 Francesco D'Amico , Dario Bocchi , Luca Maria Del Bono , Saverio Rossi , Matteo Negri

To explore the relation between network structure and function, we studied the computational performance of Hopfield-type attractor neural nets with regular lattice, random, small-world and scale-free topologies. The random net is the most…

Disordered Systems and Neural Networks · Physics 2009-11-10 Patrick N. Mcgraw , Michael Menzinger

Dense associative memory, a fundamental instance of modern Hopfield networks, can store a large number of memory patterns as equilibrium states of recurrent networks. While the stationary-state storage capacity has been investigated, its…

Disordered Systems and Neural Networks · Physics 2025-10-29 Kazushi Mimura , Jun'ichi Takeuchi , Yuto Sumikawa , Yoshiyuki Kabashima , Anthony C. C. Coolen

Associative memory models such as the Hopfield network and its dense generalizations with higher-order interactions exhibit a "blackout catastrophe" -- a discontinuous transition where stable memory states abruptly vanish when the number of…

Disordered Systems and Neural Networks · Physics 2026-03-24 David G. Clark