An associative memory is a structure learned from a dataset M of vectors (signals) in a way such that, given a noisy version of one of the vectors as input, the nearest valid vector from M (nearest neighbor) is provided as output, preferably via a fast iterative algorithm. Traditionally, binary (or q -ary) Hopfield neural networks are used to model the above structure. In this paper, for the first time, we propose a model of associative memory based on sparse recovery of signals. Our basic premise is simple. For a dataset, we learn a set of linear constraints that every vector in the dataset must satisfy. Provided these linear constraints possess some special properties, it is possible to cast the task of finding nearest neighbor as a sparse recovery problem. Assuming generic random models for the dataset, we show that it is possible to store super-polynomial or exponential number of n -length vectors in a neural network of size O ( n) . Furthermore, given a noisy version of one of the stored vectors corrupted in near-linear number of coordinates, the vector can be correctly recalled using a neurally feasible algorithm.

Dense associative memories (DAMs) store and retrieve patterns via energy-functional fixed points, but existing models are limited to vector representations. We extend DAMs to probability distributions equipped with the 2-Wasserstein distance, focusing mainly on the Bures-Wasserstein class of Gaussian densities. Our framework defines a log-sum-exp energy over stored distributions and a retrieval dynamics aggregating optimal transport maps in a Gibbs-weighted manner. Stationary points correspond to self-consistent Wasserstein barycenters, generalizing classical DAM fixed points. We prove exponential storage capacity, provide quantitative retrieval guarantees under Wasserstein perturbations, and validate the model on synthetic and real-world distributional tasks. This work elevates associative memory from vectors to full distributions, bridging classical DAMs with modern generative modeling and enabling distributional storage and retrieval in memory-augmented learning.

ABSTRACT An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neural architectures such as Transformers. This work addresses a distributed setting where agents maintain a local AM to recall their own associations as well as selective information from others. Specifically, we introduce a distributed online gradient descent method that optimizes local AMs at different agents through communication over routing trees. Our theoretical analysis establishes sublinear regret guarantees, and experiments demonstrate that the proposed protocol consistently outperforms existing online optimization baselines. Index T erms-- Associative Memory, Distributed Optimization, Online Convex Optimization 1. INTRODUCTION An associative memory (AM), a classical concept in cognitive science, stores cue-response associations, recalling the response when the corresponding cue is presented [1]. This principle, fundamental to human cognition, provides a natural abstraction for modeling how information can be efficiently retained, updated, and retrieved.

The Transformer architecture, underpinned by the self-attention mechanism, has become the de facto standard for sequence modeling tasks. However, its core computational primitive scales quadratically with sequence length (O(N^2)), creating a significant bottleneck for processing long contexts. In this paper, we propose the Gated Associative Memory (GAM) network, a novel, fully parallel architecture for sequence modeling that exhibits linear complexity (O(N)) with respect to sequence length. The GAM block replaces the self-attention layer with two parallel pathways: a causal convolution to efficiently capture local, position-dependent context, and a parallel associative memory retrieval mechanism to model global, content-based patterns. These pathways are dynamically fused using a gating mechanism, allowing the model to flexibly combine local and global information for each token. We implement GAM from scratch and conduct a rigorous comparative analysis against a standard Transformer model and a modern linear-time baseline (Mamba) on the WikiText-2 benchmark, as well as against the Transformer on the TinyStories dataset. Our experiments demonstrate that GAM is consistently faster, outperforming both baselines on training speed, and achieves a superior or competitive final validation perplexity across all datasets, establishing it as a promising and efficient alternative for sequence modeling.

Offline reinforcement learning (RL) often deals with suboptimal data when collecting large expert datasets is unavailable or impractical. This limitation makes it difficult for agents to generalize and achieve high performance, as they must learn primarily from imperfect or inconsistent trajectories. A central challenge is therefore how to best leverage scarce expert demonstrations alongside abundant but lower-quality data. We demonstrate that incorporating even a tiny amount of expert experience can substantially improve RL agent performance. We introduce Re:Frame (Retrieving Experience From Associative Memory), a plug-in module that augments a standard offline RL policy (e.g., Decision Transformer) with a small external Associative Memory Buffer (AMB) populated by expert trajectories drawn from a separate dataset. During training on low-quality data, the policy learns to retrieve expert data from the Associative Memory Buffer (AMB) via content-based associations and integrate them into decision-making; the same AMB is queried at evaluation. This requires no environment interaction and no modifications to the backbone architecture. On D4RL MuJoCo tasks, using as few as 60 expert trajectories (0.1% of a 6000-trajectory dataset), Re:Frame consistently improves over a strong Decision Transformer baseline in three of four settings, with gains up to +10.7 normalized points. These results show that Re:Frame offers a simple and data-efficient way to inject scarce expert knowledge and substantially improve offline RL from low-quality datasets.

We investigate how feature correlations influence the capacity of Dense Associative Memory (DAM), a Transformer attention-like model. Practical machine learning scenarios involve feature-correlated data and learn representations in the input space, but current capacity analyses do not account for this. We develop an empirical framework to analyze the effects of data structure on capacity dynamics. Specifically, we systematically construct datasets that vary in feature correlation and pattern separation using Hamming distance from information theory, and compute the model's corresponding storage capacity using a simple binary search algorithm. Our experiments confirm that memory capacity scales exponentially with increasing separation in the input space. Feature correlations do not alter this relationship fundamentally, but reduce capacity slightly at constant separation. This effect is amplified at higher polynomial degrees in the energy function, suggesting that Associative Memory is more limited in depicting higher-order interactions between features than patterns. Our findings bridge theoretical work and practical settings for DAM, and might inspire more data-centric methods.

Networks of phase oscillators can serve as dense associative memories if they incorporate higher-order coupling beyond the classical Kuramoto model's pairwise interactions. Here we introduce a generalized Kuramoto model with combined second-harmonic (pairwise) and fourth-harmonic (quartic) coupling, inspired by dense Hopfield memory theory. Using mean-field theory and its dynamical approximation, we obtain a phase diagram for dense associative memory model that exhibits a tricritical point at which the continuous onset of memory retrieval is supplanted by a discontinuous, hysteretic transition. In the quartic-dominated regime, the system supports bistable phase-locked states corresponding to stored memory patterns, with a sizable energy barrier between memory and incoherent states. We analytically determine this bistable region and show that the escape time from a memory state (due to noise) grows exponentially with network size, indicating robust storage. Extending the theory to finite memory load, we show that higher-order couplings achieve superlinear scaling of memory capacity with system size, far exceeding the limit of pairwise-only oscillators. Large-scale simulations of the oscillator network confirm our theoretical predictions, demonstrating rapid pattern retrieval and robust storage of many phase patterns. These results bridge the Kuramoto synchronization with modern Hopfield memories, pointing toward experimental realization of high-capacity, analog associative memory in oscillator systems.

We propose a novel energy function for Dense Associative Memory (DenseAM) networks, the log-sum-ReLU (LSR), inspired by optimal kernel density estimation. Unlike the common log-sum-exponential (LSE) function, LSR is based on the Epanechnikov kernel and enables exact memory retrieval with exponential capacity without requiring exponential separation functions. Moreover, it introduces abundant additional \emph{emergent} local minima while preserving perfect pattern recovery -- a characteristic previously unseen in DenseAM literature. Empirical results show that LSR energy has significantly more local minima (memories) that have comparable log-likelihood to LSE-based models. Analysis of LSR's emergent memories on image datasets reveals a degree of creativity and novelty, hinting at this method's potential for both large-scale memory storage and generative tasks.

We study the optimal memorization capacity of modern Hopfield models and Kernelized Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories.We present a tight analysis by establishing a connection between the memory configuration of KHMs and spherical codes from information theory. Specifically, we treat the stored memory set as a specialized spherical code.This enables us to cast the memorization problem in KHMs into a point arrangement problem on a hypersphere.We show that the optimal capacity of KHMs occurs when the feature space allows memories to form an optimal spherical code.This unique perspective leads to: 1. An analysis of how KHMs achieve optimal memory capacity, and identify corresponding necessary conditions. Importantly, we establish an upper capacity bound that matches the well-known exponential lower bound in the literature. This provides the first tight and optimal asymptotic memory capacity for modern Hopfield models.2.

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative memory (think simple linear attention) and then dive into two dimensions: Memory Capacity: How much can a Transformer really remember, and how well? We introduce retrieval SNR to measure this and use a kernel perspective to mathematically reveal why Softmax Attention is so effective. We also show how FFNs can be seen as a type of associative memory, leading to insights on their design and potential improvements. Memory Update: How do these memories learn and evolve? We present a unified framework for understanding how different Transformer variants (like DeltaNet and Softmax Attention) update their "knowledge base". This leads us to tackle two provocative questions: 1. Are Transformers fundamentally limited in what they can express, and can we break these barriers? 2. If a Transformer had infinite context, would it become infinitely intelligent? We want to demystify Transformer architecture, offering a clearer understanding of existing designs. This exploration aims to provide fresh insights and spark new avenues for Transformer innovation.