English
Related papers

Related papers: DeMo: Decoupled Momentum Optimization

200 papers

Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward…

Machine Learning · Computer Science 2025-11-05 Ashwinee Panda , Vatsal Baherwani , Zain Sarwar , Benjamin Therien , Sambit Sahu , Tom Goldstein , Supriyo Chakraborty

Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-06-17 Chi Zhang , Qianxiao Li

Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer…

Communications in highly dynamic channels relying on training-based channel estimation experience a trade-off between increasing channel measurement accuracy by sending more frequent training sequences and increasing data rate by sending…

Information Theory · Computer Science 2026-05-04 Duschia Bodet , Muriel Médard , Muralidhar Rangaswamy , Ken Duffy

Recently, min-max optimization problems have received increasing attention due to their wide range of applications in machine learning (ML). However, most existing min-max solution techniques are either single-machine or distributed…

Machine Learning · Computer Science 2023-03-07 Zhuqing Liu , Xin Zhang , Songtao Lu , Jia Liu

We study a federated version of multi-objective optimization (MOO), where a single model is trained to optimize multiple objective functions. MOO has been extensively studied in the centralized setting but is less explored in federated or…

Machine Learning · Computer Science 2025-04-22 Baris Askin , Pranay Sharma , Gauri Joshi , Carlee Joe-Wong

Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by combining complementary information from multiple modalities. Existing multi-modal object ReID methods primarily focus on the fusion of heterogeneous features.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Yuhao Wang , Yang Liu , Aihua Zheng , Pingping Zhang

Decentralized optimization with time-varying networks is an emerging paradigm in machine learning. It saves remarkable communication overhead in large-scale deep training and is more robust in wireless scenarios especially when nodes are…

Machine Learning · Computer Science 2022-11-02 Xinmeng Huang , Kun Yuan

The scale of deep learning nowadays calls for efficient distributed training algorithms. Decentralized momentum SGD (DmSGD), in which each node averages only with its neighbors, is more communication efficient than vanilla Parallel momentum…

Machine Learning · Computer Science 2021-04-27 Kun Yuan , Yiming Chen , Xinmeng Huang , Yingya Zhang , Pan Pan , Yinghui Xu , Wotao Yin

As distributed optimization scales to meet the demands of Large Language Model (LLM) training, hardware failures become increasingly non-negligible. Existing fault-tolerant training methods often introduce significant computational or…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-21 Rizhen Hu , Yutong He , Ran Yan , Mou Sun , Binghang Yuan , Kun Yuan

Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an…

Machine Learning · Computer Science 2021-06-21 Tao Lin , Sai Praneeth Karimireddy , Sebastian U. Stich , Martin Jaggi

Reducing communication complexity is critical for efficient decentralized optimization. The proximal decentralized optimization (PDO) framework is particularly appealing, as methods within this framework can exploit functional similarity…

Machine Learning · Computer Science 2025-06-09 Yuki Takezawa , Xiaowen Jiang , Anton Rodomanov , Sebastian U. Stich

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms…

Machine Learning · Computer Science 2026-02-06 Hao Chen , Jinghui Yuan , Hanmin Zhang

A novel Decentralized Noisy Model Update Tracking Federated Learning algorithm (FedNMUT) is proposed that is tailored to function efficiently in the presence of noisy communication channels that reflect imperfect information exchange. This…

Machine Learning · Computer Science 2024-03-26 Vishnu Pandi Chellapandi , Antesh Upadhyay , Abolfazl Hashemi , Stanislaw H. Żak

This paper introduces a new algorithm for trajectory optimization, Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization (DRAFTO). It first constructs a constrained objective that accounts for smoothness, safety,…

Robotics · Computer Science 2026-03-13 Yichang Feng , Xiao Liang , Minghui Zheng

Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method.…

Machine Learning · Computer Science 2026-02-05 Chenwei Cui , Rockwell Jackson , Benjamin Joseph Herrera , Ana María Tárano , Hannah Kerner

This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Runmin Zhang , Jialiang Wang , Si-Yuan Cao , Zhu Yu , Junchen Yu , Guangyi Zhang , Hui-Liang Shen

We study decentralized optimization where multiple agents minimize the average of their (strongly) convex, smooth losses over a communication graph. Convergence of the existing decentralized methods generally hinges on an apriori, proper…

Optimization and Control · Mathematics 2025-08-01 Ilya Kuruzov , Xiaokai Chen , Gesualdo Scutari , Alexander Gasnikov

Scaling to arbitrarily large bundle adjustment problems requires data and compute to be distributed across multiple devices. Centralized methods in prior works are only able to solve small or medium size problems due to overhead in…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Taosha Fan , Joseph Ortiz , Ming Hsiao , Maurizio Monge , Jing Dong , Todd Murphey , Mustafa Mukadam

Lightweight Large Language Models (LwLLMs) are reduced-parameter, optimized models designed to run efficiently on consumer-grade hardware, offering significant advantages in resource efficiency, cost-effectiveness, and data privacy.…

Computation and Language · Computer Science 2025-06-10 Hongming Yang , Shi Lin , Jun Shao , Changting Lin , Donghai Zhu , Meng Han , Qinglei Kong