English
Related papers

Related papers: Multi-Headed Transformer Architectures as Time-dep…

200 papers

This thesis analyze the Wasserstein gradient flow of a functional defined as a double convolution of a non-smooth repulsive interaction potential. To be more precise, the potential under investigation has a -|x| behavior close to the…

Analysis of PDEs · Mathematics 2013-10-15 Giovanni A. Bonaschi

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

Computation and Language · Computer Science 2024-07-16 Sai Sena Chinnakonduru , Astarag Mohapatra

We propose a data-based method to solve a multi-stage stochastic optimal power flow (OPF) problem based on limited information about forecast error distributions. The framework explicitly combines multi-stage feedback policies with any…

Optimization and Control · Mathematics 2018-10-29 Yi Guo , Kyri Baker , Emiliano Dall'Anese , Zechun Hu , Tyler H. Summers

We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein…

Machine Learning · Computer Science 2026-02-02 Philippe Rigollet

The Transformer, a breakthrough architecture in artificial intelligence, owes its success to the attention mechanism, which utilizes long-range interactions in sequential data, enabling the emergent coherence between large language models…

Artificial Intelligence · Computer Science 2026-04-23 Zihan Zhou , Bo-Wei Qin , Kai Du , Wei Lin

We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping points) at which efficient Transformer variants become more…

Computation and Language · Computer Science 2023-06-16 Anuj Diwan , Eunsol Choi , David Harwath

In the present work, a new time-dependent exchange theory is presented wherein the symmetry constraints, on a multi-electron wavefunction, are properly accounted for. In so doing, the equations of motion, incorporating the required…

Computational Physics · Physics 2007-05-23 Charles A. Weatherford

This paper presents a Wasserstein attraction approach for solving dynamic mass transport problems over networks. In the transport problem over networks, we start with a distribution over the set of nodes that needs to be "transported" to a…

Optimization and Control · Mathematics 2022-04-28 Ferran Arqué , César A. Uribe , Carlos Ocampo-Martinez

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

We study data-driven decision problems where historical observations are generated by a time-evolving distribution whose consecutive shifts are bounded in Wasserstein distance. We address this nonstationarity using a distributionally robust…

Optimization and Control · Mathematics 2025-12-25 Dominic S. T. Keehan , Edward J. Anderson , Wolfram Wiesemann

We make the information transmitted by attention an explicit, measurable quantity in vision transformers. By inserting variational information bottlenecks on all attention-mediated writes to the residual stream -- without other…

Machine Learning · Computer Science 2026-02-05 Kieran A. Murphy

The traffic assignment problem is essential for traffic flow analysis, traditionally solved using mathematical programs under the Equilibrium principle. These methods become computationally prohibitive for large-scale networks due to…

Machine Learning · Computer Science 2026-04-28 Mostafa Ameli , Sulthana Shams , Van Anh Le , Alexander Skabardonis

Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling transformer…

Machine Learning · Computer Science 2025-04-17 Anh Tong , Thanh Nguyen-Tang , Dongeun Lee , Duc Nguyen , Toan Tran , David Hall , Cheongwoong Kang , Jaesik Choi

We prove the existence of weak solutions to a system of two diffusion equations that are coupled by a pointwise volume constraint. The time evolution is given by gradient dynamics for a free energy functional. Our primary example is a model…

Analysis of PDEs · Mathematics 2020-03-18 Clément Cancès , Daniel Matthes

Graph Transformer (GT), as a special type of Graph Neural Networks (GNNs), utilizes multi-head attention to facilitate high-order message passing. However, this also imposes several limitations in node classification applications: 1) nodes…

Machine Learning · Computer Science 2024-10-16 Jiajun Zhou , Xuanze Chen , Chenxuan Xie , Yu Shanqing , Qi Xuan , Xiaoniu Yang

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Computation and Language · Computer Science 2026-05-20 Jiaoda Li , Ryan Cotterell

We study the stability of multi-layer radial flows in porous media within the Hele-Shaw model. We perform a linear stability analysis for radial flows consisting of an arbitrary number of fluid layers with interfaces separating fluids of…

Fluid Dynamics · Physics 2018-11-28 Craig Gin , Prabir Daripa

We model the evolution of tokens within a deep stack of Transformer layers as a continuous-time flow on the unit sphere, governed by a mean-field interacting particle system, building on the framework introduced in (Geshkovski et al.,…

Machine Learning · Computer Science 2025-04-17 Giuseppe Bruno , Federico Pasqualotto , Andrea Agazzi

The modeling of high-dimensional spatio-temporal processes presents a fundamental dichotomy between the probabilistic rigor of classical geostatistics and the flexible, high-capacity representations of deep learning. While Gaussian…

Machine Learning · Computer Science 2025-12-22 Yuri Calleo