paper-with-me

Papers

Linear Speedup in Personalized Collaborative Learning

2021-11-10 · El Mahdi Chayti, Sai Praneeth Karimireddy, Sebastian U. Stich, Nicolas Flammarion, Martin Jaggi

Collaborative training can improve the accuracy of a model for a user by trading off the model's bias (introduced by using data from other users who are potentially different) against its variance (due to the limited amount of data on any single user). In this work, we formalize the personalized collaborative learning problem as a stochastic optimization of a task 0 while giving access to N related but different tasks 1,..., N. We provide convergence guarantees for two algorithms in this setting -- a popular collaboration method known as weighted gradient averaging, and a novel bias correction method -- and explore conditions under which we can achieve linear speedup w.r.t. the number of auxiliary tasks N. Further, we also empirically study their performance confirming our theoretical insights.

📄 PDF Abstract BibTeX arXiv:2111.05968

Code (1)

elmahdichayti/linspeedupcode 공식 구현

Tasks

Federated LearningStochastic Optimization

Similar Papers 제목 키워드 기반

Personalized Collaborative Learning with Affinity-Based Variance Reduction

2025-10-17 · Chenyu Zhang, Navid Azizan arxiv

Multi-agent learning faces a fundamental tension: leveraging distributed collaboration without sacrificing the personalization needed for diverse agents. This tension intensifies when aiming for full personalization whil…

Federated Learning

DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations

2023-12-17 · Guojun Xiong, Gang Yan, Shiqiang Wang, Jian Li

Decentralized learning has emerged as an alternative method to the popular parameter-server framework which suffers from high communication burden, single-point failure and scalability issues due to the need of a central…

Learning TheoryRepresentation Learning

On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations

2024-11-22 · Guojun Xiong, Shufan Wang, Daniel Jiang, Jian Li

Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment interactions. However, in practice, the envir…

Sparse Federated Learning with Hierarchical Personalized Models

2022-03-25 · Xiaofeng Liu, Qing Wang, Yunfeng Shao, Yinchuan Li

Federated learning (FL) can achieve privacy-safe and reliable collaborative training without collecting users' private data. Its excellent privacy security potential promotes a wide range of FL applications in Internet-o…

Autonomous VehiclesFederated Learning

Personalized Federated Learning with Moreau Envelopes

2020-06-16 · NeurIPS 2020 12 · Canh T. Dinh, Nguyen H. Tran, Tuan Dung Nguyen

Federated learning (FL) is a decentralized and privacy-preserving machine learning technique in which a group of clients collaborate with a server to learn a global model without sharing clients' data. One challenge asso…

DiversityFederated LearningMeta-LearningModel Optimization+3