English
Related papers

Related papers: When and Why Grouping Attention Heads Accelerates …

200 papers

Semi-dense feature matching methods have been significantly advanced by leveraging attention mechanisms to extract discriminative descriptors. However, most existing approaches treat all pixels equally during attention computations, which…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Dongyue Li

The problem of synchronization over a group $\mathcal{G}$ aims to estimate a collection of group elements $G^*_1, \dots, G^*_n \in \mathcal{G}$ based on noisy observations of a subset of all pairwise ratios of the form $G^*_i {G^*_j}^{-1}$.…

Optimization and Control · Mathematics 2023-06-19 Huikang Liu , Man-Chung Yue , Anthony Man-Cho So

We study the factors affecting training time in multi-device deep learning systems. Given a specification of a convolutional neural network, our goal is to minimize the time to train this model on a cluster of commodity CPUs and GPUs. We…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-10-20 Stefan Hadjis , Ce Zhang , Ioannis Mitliagkas , Dan Iter , Christopher Ré

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Computation and Language · Computer Science 2020-08-11 Sneha Mehta , Huzefa Rangwala , Naren Ramakrishnan

Many approaches for addressing Global Optimization problems typically rely on relaxations of nonlinear constraints over specific mathematical primitives. This is restricting in applications with constraints that are black-box, implicit or…

Optimization and Control · Mathematics 2025-01-03 Dimitris Bertsimas , Georgios Margaritis

Supervised fine-tuning (SFT) has become an essential step in tailoring large language models (LLMs) to align with human expectations and specific downstream tasks. However, existing SFT methods typically treat each training instance as a…

Machine Learning · Computer Science 2025-06-19 Gyuhak Kim , Sumiran Singh Thakur , Su Min Park , Wei Wei , Yujia Bao

Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates to promote stability,…

Machine Learning · Computer Science 2026-02-23 Minxin Zhang , Yuxuan Liu , Hayden Schaeffer

Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout budget is small,…

Machine Learning · Computer Science 2026-02-02 Youngeun Kim

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Dongshuo Yin , Leiyi Hu , Bin Li , Youqun Zhang , Xue Yang

Batch Whitening is a technique that accelerates and stabilizes training by transforming input features to have a zero mean (Centering) and a unit variance (Scaling), and by removing linear correlation between channels (Decorrelation). In…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Yooshin Cho , Hanbyel Cho , Youngsoo Kim , Junmo Kim

In contrast to Part I of this treatise [1] that focuses on the optimization problems associated with single matrix variables, in this paper, we investigate the application of the matrix-monotonic optimization framework in the optimization…

Information Theory · Computer Science 2021-02-24 Chengwen Xing , Shuai Wang , Sheng Chen , Shaodan Ma , H. Vincent Poor , Lajos Hanzo

Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Thomas Woergaard , Raghavendra Selvan

Despite the high importance of grouping in practice, there exists little research on the respective topic. The present work presents a complete framework for grouping and a novel method to optimize model points. Model points are used to…

Risk Management · Quantitative Finance 2019-12-23 Mark Kiermayer , Christian Weiß

In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis. However, attention module variants featured in various research papers often operate under diverse settings and tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Chengzhi Wu , Kaige Wang , Zeyun Zhong , Hao Fu , Junwei Zheng , Jiaming Zhang , Julius Pfrommer , Jürgen Beyerer

This paper proposes Medley of Sub-Attention Networks (MoSAN), a new novel neural architecture for the group recommendation task. Group-level recommendation is known to be a challenging task, in which intricate group dynamics have to be…

Artificial Intelligence · Computer Science 2019-12-02 Lucas Vinh Tran , Tuan-Anh Nguyen Pham , Yi Tay , Yiding Liu , Gao Cong , Xiaoli Li

People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and more biased toward the…

Machine Learning · Computer Science 2020-10-02 Xiaoliang Luo , Brett D. Roads , Bradley C. Love

Recommender systems (RecSys) are increasingly emphasizing scaling, leveraging larger architectures and more interaction data to improve personalization. Yet, despite the optimizer's pivotal role in training, modern RecSys pipelines almost…

Information Retrieval · Computer Science 2026-03-03 Rong Shan , Aofan Yu , Bo Chen , Kuo Cai , Qiang Luo , Ruiming Tang , Han Li , Weiwen Liu , Weinan Zhang , Jianghao Lin

Point cloud analysis has evolved with diverse network architectures, while existing works predominantly focus on introducing novel structural designs. However, conventional point-based architectures - processing raw points through…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Shangzhuo Xie , Qianqian Yang

Equivariant neural networks encode geometric symmetries by construction, yet they are often difficult to optimize and can underperform less constrained architectures. A growing body of work addresses this through architectural modifications…

Machine Learning · Computer Science 2026-05-28 Teodor-Mihai Stupariu , Andrei Manolache