Nov 2022· Conference on Learning for Dynamics & Control· pp. 1308-1320· 28 citations· ⚡ 2 influential· 31 references
Computer ScienceEngineeringMathematics
TL;DR
This work addresses the question of how multiple clients collaboratively learn dynamical models in the presence of heterogeneity by posing the problem as a federated learning problem and characterize the tension between achievable performance and system heterogeneity.
Abstract
We study the problem of learning a linear system model from the observations of $M$ clients. The catch: Each client is observing data from a different dynamical system. This work addresses the question of how multiple clients collaboratively learn dynamical models in the presence of heterogeneity. We pose this problem as a federated learning problem and characterize the tension between achievable performance and system heterogeneity. Furthermore, our federated sample complexity result provides a constant factor improvement over the single agent setting. Finally, we describe a meta federated learning algorithm, FedSysID, that leverages existing federated algorithms at the client level.
Federated learning (FL) enables collaborative model training without centralizing clients’ raw data, but parameter exchange can impose substantial communication costs and usually requires compatible model architectures. Federated distillation (FD) instead transfers predictive or intermediate knowledge through knowledge...
Lin Li, Jian-Ping Gou, Bao-Sheng Yu et al.· ACM Computing Surveys· 1 citation
We study personalized federated linear stochastic approximation (LSA), a framework which notably encompass personalized temporal difference learning. In this setting, heterogeneous agents collaborate to solve distinct linear fixed-point equations, each corresponding to an agent-specific learning problem. A central open...
Safwan Labbi, Paul Mangold, Eric Moulines· 0 citations
FedTOPS (Federated Teacher-guided On-Policy Scaling), which reuses teacher feedback on current trajectories to adapt the FedAvg update magnitude under clientwise predictive-change constraints is proposed.
Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient training of a global model. In this study, we propose a novel latent information sharing scheme that directly mitigates data heterogeneity across...
Seung-Jun Lee, Ensieh Khazaei, Dimitrios Hatzinakos et al.· 0 citations
A global ambiguity set is constructed as the union of admissible mixtures of local ambiguity sets that allows client-specific ambiguity radii and admits a client-wise separable reformulation and establishes a high-probability out-of-sample performance guarantee.
Ying-Zhu Liu, Zhong-Kui Li, Peng-Cheng You et al.· 0 citations
FedPCD is proposed, a priority-constrained federated optimization framework that separates the global optimization objective from client protection, and preserves the conventional federated aggregate as the primary objective, while allowing only the minimum correction necessary to meet client performance constraints.
Yousef Irshaid, Dara Varam, Mohamed I. Alhajri· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
