English
Related papers

Related papers: DeMo: Decoupled Momentum Optimization

200 papers

Asynchronous algorithms have attracted much attention recently due to the crucial demands on solving large-scale optimization problems. However, the accelerated versions of asynchronous algorithms are rarely studied. In this paper, we…

Optimization and Control · Mathematics 2018-02-28 Cong Fang , Yameng Huang , Zhouchen Lin

Decentralized bilevel optimization has received increasing attention recently due to its foundational role in many emerging multi-agent learning paradigms (e.g., multi-agent meta-learning and multi-agent reinforcement learning) over…

Machine Learning · Computer Science 2023-01-23 Peiwen Qiu , Yining Li , Zhuqing Liu , Prashant Khanduri , Jia Liu , Ness B. Shroff , Elizabeth Serena Bentley , Kurt Turck

To reduce the computational and memory overhead of Large Language Models, various approaches have been proposed. These include a) Mixture of Experts (MoEs), where token routing affects compute balance; b) gradual pruning of model…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-16 Mohamed Wahib , Muhammed Abdullah Soyturk , Didem Unat

In this paper, we propose and analyze SQuARM-SGD, a communication-efficient algorithm for decentralized training of large-scale machine learning models over a network. In SQuARM-SGD, each node performs a fixed number of local SGD steps…

Machine Learning · Computer Science 2021-10-12 Navjot Singh , Deepesh Data , Jemin George , Suhas Diggavi

In distributed optimization and federated learning, asynchronous alternating direction method of multipliers (ADMM) serves as an attractive option for large-scale optimization, data privacy, straggler nodes and variety of objective…

Machine Learning · Computer Science 2025-08-19 Sagar Shrestha

We consider a decentralized optimization problem for networks affected by communication delays. Examples of such networks include collaborative machine learning, sensor networks, and multi-agent systems. To mimic communication delays, we…

Machine Learning · Computer Science 2024-10-03 Tomas Ortega , Hamid Jafarkhani

Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular…

Machine Learning · Computer Science 2025-04-18 Ye Yuan , Youyuan Zhang , Can Chen , Haolun Wu , Zixuan Li , Jianmo Li , James J. Clark , Xue Liu

Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type adaptive learning rates that can be used on top of any momentum…

Machine Learning · Computer Science 2024-06-06 Fabian Schaipp , Ruben Ohana , Michael Eickenberg , Aaron Defazio , Robert M. Gower

In modern parametric model training, full-batch gradient descent (and its variants) suffers due to progressively stronger biasing towards the exact realization of training data; this drives the systematic ``generalization gap'', where the…

Statistics Theory · Mathematics 2026-05-01 Max Lovig

PDE-Constrained Optimization (PDECO) problems can be accelerated significantly by employing gradient-based methods with surrogate models like neural operators compared to traditional numerical solvers. However, this approach faces two key…

Machine Learning · Computer Science 2025-06-17 Ze Cheng , Zhuoyu Li , Xiaoqiang Wang , Jianing Huang , Zhizhou Zhang , Zhongkai Hao , Hang Su

The sparsely activated mixture-of-experts (MoE) transformer has become a common architecture for large language models (LLMs) due to its sparsity, which requires fewer computational demands while easily scaling the model size. In MoE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-14 Wenxiang Lin , Xinglin Pan , Lin Zhang , Shaohuai Shi , Xuan Wang , Xiaowen Chu

Consensus-based distributed optimization methods have recently been advocated as alternatives to parameter server and ring all-reduce paradigms for large scale training of machine learning models. In this case, each worker maintains a local…

Machine Learning · Computer Science 2020-03-02 Giovanni Neglia , Chuan Xu , Don Towsley , Gianmarco Calbi

We consider a multi-agent network where each node has a stochastic (local) cost function that depends on the decision variable of that node and a random variable, and further the decision variables of neighboring nodes are pairwise…

Optimization and Control · Mathematics 2021-12-24 Navjot Singh , Xuanyu Cao , Suhas Diggavi , Tamer Basar

Modern machine learning tasks often involve massive datasets and models, necessitating distributed optimization algorithms with reduced communication overhead. Communication compression, where clients transmit compressed updates to a…

Optimization and Control · Mathematics 2025-04-01 Yuan Gao , Anton Rodomanov , Jeremy Rack , Sebastian U. Stich

This paper introduces a SSSUMO, semi-supervised deep learning approach for submovement decomposition that achieves state-of-the-art accuracy and speed. While submovement analysis offers valuable insights into motor control, existing methods…

Human-Computer Interaction · Computer Science 2025-07-14 Evgenii Rudakov , Jonathan Shock , Otto Lappi , Benjamin Ultan Cowley

Federated learning enables collaborative model training across numerous edge devices without requiring participants to share data; however, memory and communication constraints on these edge devices may preclude their participation in…

Machine Learning · Computer Science 2025-09-04 Gwen Legate , Irina Rish , Eugene Belilovsky

Continual Model Merging (CMM) enables rapid customization of foundation models by sequentially incorporating task-adapted models without repeated retraining. However, existing merging rules usually update the deployed model through fixed…

Machine Learning · Computer Science 2026-05-26 Lihong Lin , Haidong Kang

Federated Composite Optimization (FCO) has emerged as a promising framework for training models with structural constraints (e.g., sparsity) in distributed edge networks. However, simultaneously achieving communication efficiency and…

Optimization and Control · Mathematics 2026-03-10 Pu Qiu , Chen Ouyang , Yongyang Xiong , Keyou You , Wanquan Liu , Yang Shi

Decomposition has become an increasingly popular technique for evolutionary multi-objective optimization (EMO). A decomposition-based EMO algorithm is usually designed to approximate a whole Pareto-optimal front (PF). However, in practice,…

Neural and Evolutionary Computing · Computer Science 2018-10-02 Ke Li , Renzhi Chen , Dragan Savic , Xin Yao

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular…

Hardware Architecture · Computer Science 2024-03-19 Yansong Xu , Dongxu Lyu , Zhenyu Li , Zilong Wang , Yuzhou Chen , Gang Wang , Zhican Wang , Haomin Li , Guanghui He