English
Related papers

Related papers: Sinkhorn Based Associative Memory Retrieval Using …

200 papers

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…

Machine Learning · Statistics 2024-11-04 Jerry Yao-Chieh Hu , Dennis Wu , Han Liu

This work studies the entropic regularization formulation of the 2-Wasserstein distance on an infinite-dimensional Hilbert space, in particular for the Gaussian setting. We first present the Minimum Mutual Information property, namely the…

Machine Learning · Statistics 2022-03-15 Minh Ha Quang

We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport…

Optimization and Control · Mathematics 2025-03-27 Jie Wang , Rui Gao , Yao Xie

We investigate the problem of quantifying contraction coefficients of Markov transition kernels in Kantorovich ($L^1$ Wasserstein) distances. For diffusion processes, relatively precise quantitative bounds on contraction rates have recently…

Probability · Mathematics 2018-08-22 Andreas Eberle , Mateusz B. Majka

Entropic optimal transport problems play an increasingly important role in machine learning and generative modelling. In contrast with optimal transport maps which often have limited applicability in high dimensions, Schrodinger bridges can…

Probability · Mathematics 2026-01-21 Pierre Del Moral , Ajay Jasra

We study a class of Hopfield models where the memories are represented by a mixture of Gaussian and binary variables and the neurons are Ising spins. We study the properties of this family of models as the relative weight of the two kinds…

Disordered Systems and Neural Networks · Physics 2022-09-29 Luca Leuzzi , Alberto Patti , Federico Ricci-Tersenghi

We develop an adjoint approach for recovering the topographical function included in the source term of one-dimensional hyperbolic balance laws. We focus on a specific system, namely the shallow water equations, in an effort to recover the…

Optimization and Control · Mathematics 2021-04-06 Jolene Britton , Yat Tin Chow , Weitao Chen , Yulong Xing

Solutions to the Schr\"{o}dinger bridge problem and its generalizations yield feedback control policies for optimal density steering over a controlled diffusion. To numerically compute the same, the dynamic Sinkhorn recursion has become a…

Optimization and Control · Mathematics 2026-04-28 Georgiy A. Bondar , Asmaa Eldesoukey , Yongxin Chen , Abhishek Halder

Restricted Boltzmann Machines are key tools in Machine Learning and are described by the energy function of bipartite spin-glasses. From a statistical mechanical perspective, they share the same Gibbs measure of Hopfield networks for…

Mathematical Physics · Physics 2017-08-02 Elena Agliari , Adriano Barra , Chiara Longo , Daniele Tantari

This paper is devoted to the stochastic approximation of entropically regularized Wasserstein distances between two probability measures, also known as Sinkhorn divergences. The semi-dual formulation of such regularized optimal…

Statistics Theory · Mathematics 2024-12-10 Bernard Bercu , Jérémie Bigot

We improve a phase retrieval approach that uses correlation-based measurements with compactly supported measurement masks [27]. The improved algorithm admits deterministic measurement constructions together with a robust, fast recovery…

Numerical Analysis · Mathematics 2016-12-07 Mark A. Iwen , Brian Preskitt , Rayan Saab , Aditya Viswanathan

This work studies the convergence and finite sample approximations of entropic regularized Wasserstein distances in the Hilbert space setting. Our first main result is that for Gaussian measures on an infinite-dimensional Hilbert space,…

Machine Learning · Statistics 2021-02-16 Minh Ha Quang

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

The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence, has recently gained popularity in machine learning and statistics, as it makes feasible the use of smoothed optimal transportation distances for data…

Statistics Theory · Mathematics 2019-11-05 Jérémie Bigot , Elsa Cazelles , Nicolas Papadakis

High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit strong storage capabilities, but the dynamical and geometric mechanisms underlying their stability remain poorly understood. This paper investigates the…

Neural and Evolutionary Computing · Computer Science 2026-05-12 Akira Tamamori

Associative memory models are content-addressable memory systems fundamental to biological intelligence and are notable for their high interpretability. However, existing models evaluate the quality of retrieval based on proximity, which…

Machine Learning · Computer Science 2025-11-26 Shurong Wang , Yuqi Pan , Zhuoyang Shen , Meng Zhang , Hongwei Wang , Guoqi Li

Real-world physical signals are continuous and high-dimensional, yet the statistical-mechanics machinery of associative memory operates on discrete Ising spins. We bridge this divide through a multilayer Ising framework that couples a…

Disordered Systems and Neural Networks · Physics 2026-05-15 Andrea Ladiana

The squared Wasserstein distance is a natural quantity to compare probability distributions in a non-parametric setting. This quantity is usually estimated with the plug-in estimator, defined via a discrete optimal transport problem which…

Optimization and Control · Mathematics 2020-10-30 Lenaic Chizat , Pierre Roussillon , Flavien Léger , François-Xavier Vialard , Gabriel Peyré

We propose and analyze a new variation of the so-called {\em exponential Hopfield model}, a recently introduced family of associative neural networks with unprecedented storage capacity. Our construction is based on a cost function defined…

Disordered Systems and Neural Networks · Physics 2025-09-09 Linda Albanese , Andrea Alessandrelli , Adriano Barra , Peter Sollich

We develop a discrete optimal transport framework for analyzing simulated annealing algorithms on finite state spaces. Building on the discrete Wasserstein metric introduced by Maas (J. Funct. Anal., 2011), we define a generalized discrete…

Data Structures and Algorithms · Computer Science 2026-05-08 Yuchen He , Tianhui Jiang , Sihan Wang , Chihao Zhang