English
Related papers

Related papers: Scaled-Dot-Product Attention as One-Sided Entropic…

200 papers

Scaled dot-product attention (SDPA) is a fundamental component responsible for the success of large-language models and other nonlinear signal processing applications. The rationale for SDPA has been based upon "query, key, value" concepts…

Machine Learning · Computer Science 2026-02-04 Terence D Sanger

From natural language processing to vision, Scaled Dot Product Attention (SDPA) is the backbone of most modern deep learning applications. Unfortunately, its memory and computational requirements can be prohibitive in low-resource settings.…

Machine Learning · Computer Science 2025-02-18 Peyman Hosseini , Mehran Hosseini , Ignacio Castro , Matthew Purver

Transformer models serve as the backbone of many state-ofthe-art language models, and most use the scaled dot-product attention (SDPA) mechanism to capture relationships between tokens. However, the straightforward implementation of SDPA…

Hardware Architecture · Computer Science 2024-08-09 Gina Sohn , Nathan Zhang , Kunle Olukotun

Attention regulates information transfer between tokens. For this, query and key vectors are compared, typically in terms of a scalar product, $\mathbf{Q}^T\mathbf{K}$, together with a subsequent softmax normalization. In geometric terms,…

Machine Learning · Computer Science 2025-08-11 Claudius Gros

Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we propose an implicit generative learning-based framework…

Machine Learning · Computer Science 2019-06-26 Yujia Xie , Minshuo Chen , Haoming Jiang , Tuo Zhao , Hongyuan Zha

We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between continuous probability distributions which are accessible by samples. Our algorithm is based on the saddle point…

Machine Learning · Computer Science 2023-11-02 Nikita Gushchin , Alexander Kolesov , Alexander Korotin , Dmitry Vetrov , Evgeny Burnaev

Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal…

Machine Learning · Statistics 2026-05-19 Naman Agarwal , Siddhartha R. Dalal , Vishal Misra

The Sinkhorn--Knopp (SK) algorithm is a cornerstone method for matrix scaling and entropically regularized optimal transport (EOT). Despite its empirical efficiency, existing theoretical guarantees to achieve a target marginal accuracy…

Data Structures and Algorithms · Computer Science 2026-04-07 Kun He

Optimal transport (OT) defines a powerful framework to compare probability distributions in a geometrically faithful way. However, the practical impact of OT is still limited because of its computational burden. We propose a new class of…

Optimization and Control · Mathematics 2016-05-30 Genevay Aude , Marco Cuturi , Gabriel Peyré , Francis Bach

While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention…

Machine Learning · Computer Science 2025-07-15 Ashkan Shahbazi , Elaheh Akbari , Darian Salehi , Xinran Liu , Navid Naderializadeh , Soheil Kolouri

Visual domain adaptation aims to learn discriminative and domain-invariant representation for an unlabeled target domain by leveraging knowledge from a labeled source domain. Partial domain adaptation (PDA) is a general and practical…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Yi-Ming Zhai , Chuan-Xian Ren , Hong Yan

Recent progress in geometric deep learning has drawn increasing attention from the machine learning community toward domain adaptation on symmetric positive definite (SPD) manifolds, especially for neuroimaging data that often suffer from…

Machine Learning · Computer Science 2025-05-09 Ce Ju , Cuntai Guan

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Computation and Language · Computer Science 2024-06-21 Martin Courtois , Malte Ostendorff , Leonhard Hennig , Georg Rehm

Doubly-stochastic attention has emerged as a transport-based alternative to row-softmax attention, with recent Transformer variants using it to reduce attention sinks and rank collapse while improving performance. In this family, the…

Machine Learning · Computer Science 2026-05-14 Huy Tran , Max Milkert , David Hyde

Learning conditional distributions $\pi^*(\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \sim \pi^*$. However, acquiring paired data samples is often…

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-size is…

Signal Processing · Electrical Eng. & Systems 2020-07-10 Zhan Gao , Alec Koppel , Alejandro Ribeiro

Scaled dot-product attention applies a softmax function on the scaled dot-product of queries and keys to calculate weights and then multiplies the weights and values. In this work, we study how to improve the learning of scaled dot-product…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Kaikai Zhao , Norimichi Ukita

In this report, we study decentralized stochastic optimization to minimize a sum of smooth and strongly convex cost functions when the functions are distributed over a directed network of nodes. In contrast to the existing work, we use…

Machine Learning · Computer Science 2020-07-24 Muhammad I. Qureshi , Ran Xin , Soummya Kar , Usman A. Khan

Distributed descent-based methods are an essential toolset to solving optimization problems in multi-agent system scenarios. Here the agents seek to optimize a global objective function through mutual cooperation. Oftentimes, cooperation is…

Optimization and Control · Mathematics 2019-08-28 Arunselvan Ramaswamy

This paper addresses the cooperative Multi-Vehicle Dynamic Pickup and Delivery Problem with Stochastic Requests (MVDPDPSR) and proposes an end-to-end centralized decision-making framework based on sequence-to-sequence, named Multi-Agent…

Machine Learning · Computer Science 2025-12-18 Zengyu Zou , Jingyuan Wang , Yixuan Huang , Junjie Wu
‹ Prev 1 2 3 10 Next ›