惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

GbyAI
GbyAI
The GitHub Blog
The GitHub Blog
小众软件
小众软件
美团技术团队
博客园 - 司徒正美
G
Google Developers Blog
Blog — PlanetScale
Blog — PlanetScale
Hugging Face - Blog
Hugging Face - Blog
博客园_首页
大猫的无限游戏
大猫的无限游戏
罗磊的独立博客
Recent Announcements
Recent Announcements
酷 壳 – CoolShell
酷 壳 – CoolShell
D
Docker
J
Java Code Geeks
Last Week in AI
Last Week in AI
V
Visual Studio Blog
Microsoft Azure Blog
Microsoft Azure Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
P
Proofpoint News Feed
V
V2EX
C
Check Point Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
MyScale Blog
MyScale Blog

cs.LG updates on arXiv.org

Memory-Guided Trust-Region Bayesian Optimization (MG-TuRBO) for High Dimensions EngageTriBoost: Predictive Modeling of User Engagement in Digital Mental Health Intervention Using Explainable Machine Learning Reservoir observer enhanced with residual calibration and attention mechanism Efficient RL Training for LLMs with Experience Replay Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing Adaptive Simulation Experiment for LLM Policy Optimization EvoLen: Evolution-Guided Tokenization for DNA Language Model Smartwatch-Based Sitting Time Estimation in Real-World Office Settings Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis Loom: A Scalable Analytical Neural Computer Architecture Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds How does Chain of Thought decompose complex tasks? Uncertainty-Aware Transformers: Conformal Prediction for Language Models Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization Using Synthetic Data for Machine Learning-based Childhood Vaccination Prediction in Narok, Kenya Delve into the Applicability of Advanced Optimizers for Multi-Task Learning Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication Predictive Entropy Links Calibration and Paraphrase Sensitivity in Medical Vision-Language Models Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge Feature-Label Modal Alignment for Robust Partial Multi-Label Learning Integrated electro-optic attention nonlinearities for transformers Toward World Models for Epidemiology Tracing the Chain: Deep Learning for Stepping-Stone Intrusion Detection Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods
Gradient Flow Structure and Quantitative Dynamics of Mult...
Ayan Pendhar · 2026-05-07 · via cs.LG updates on arXiv.org

View PDF HTML (experimental)

Abstract:Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and tend to form clusters. While prior work has established clustering behavior for single-head attention, the multi-head setting remains less understood due to geometric interference between heads, which invalidates standard monotonicity arguments.
In this work, we develop a theoretical framework for multi-head self-attention dynamics and resolve several open questions. We show that, under suitable conditions on the score matrices, a natural multi-head energy functional is non-decreasing along both flat and spherical dynamics. We identify the key obstruction to per-head monotonicity as radial shadow terms, which are projections of each head's output onto token directions, persisting even under orthogonality assumptions. We introduce a sufficient condition ensuring monotonicity and establish robustness to approximate orthogonality.
In a simplified scalar-head regime with equiangular token configurations, we derive a closed-form expression for the critical inverse temperature governing clustering behavior, and show that heterogeneous heads exhibit super-additive clustering rates. In this regime, we also prove a separation in clustering time between ReLU and softmax attention in the linearized dynamics. Finally, we establish an entropy production identity and show that attention entropy increases monotonically toward equilibrium as clustering progresses.
Our results provide a unified perspective on the dynamics of multi-head attention and clarify the mechanisms underlying clustering and stability in transformer models.
Comments: 20 pages, 5 figures
Subjects: Machine Learning (cs.LG)
MSC classes: 68T07, 35Q89, 37N40
ACM classes: I.2.6; G.2.1; F.2.0
Cite as: arXiv:2605.04279 [cs.LG]
  (or arXiv:2605.04279v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2605.04279

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ayan Pendharkar [view email]
[v1] Tue, 5 May 2026 20:31:11 UTC (794 KB)