mlsanityData to 14 Oct 2026

Adversarially Robust Multitask Adaptive Control

arXiv 2511.05444 ↗First posted 7 Nov 2025cs.LG cs.SY eess.SYcited by 1

Not on the map. Why?

Abstract (arXiv)

We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple systems collaboratively learn control policies under model uncertainty and adversarial corruption. We propose a clustered multitask approach that integrates clustering and system identification with resilient aggregation to mitigate corrupted model updates. Our analysis characterizes how clustering accuracy, intra-cluster heterogeneity, and adversarial behavior affect the expected regret of certainty-equivalent (CE) control across LQR tasks. We establish non-asymptotic bounds demonstrating that the regret decreases inversely with the number of honest systems per cluster and that this reduction is preserved under a bounded fraction of adversarial systems within each cluster.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 7 Nov 2025.

Builds on

23 of 34 references.

References · 23

  1. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  2. 2020Naive Exploration is Optimal for Online LQRcited by 116
  3. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
  4. 2018Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulatorcited by 86
  5. 2018DRACO: Byzantine-resilient Distributed Training via Redundant Gradientscited by 75
  6. 2019Learning Linear-Quadratic Regulators Efficiently with only √T Regretcited by 70
  7. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
  8. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  9. 2019The Nonstochastic Control Problemcited by 52
  10. 2020Logarithmic Regret for Learning Linear Quadratic Regulators Efficientlycited by 35
  11. 2021Stabilizing Dynamical Systems via Policy Gradient Methodscited by 25
  12. 2023Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approachcited by 23
11 more
  1. 2022FedSysID: A Federated Approach to Sample-Efficient System Identificationcited by 17
  2. 2024Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQRcited by 17
  3. 2022Identifying the Dynamics of a System by Leveraging Data from Similar Systemscited by 15
  4. 2023Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Datacited by 13
  5. 2022Regret Lower Bounds for Learning Linear Quadratic Gaussian Systemscited by 11
  6. 2023Learning Personalized Models with Clustered System Identificationcited by 11
  7. 2023Byzantine-Robust Distributed Online Learning: Taming Adversarial Participants in An Adversarial Environmentcited by 8
  8. 2023Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecificationcited by 6
  9. 2024Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Controlcited by 4
  10. 2025Learning Stabilizing Policies via an Unstable Subspace Representationcited by 3
  11. 2025Redefining Clustered Federated Learning for System Identification: The Path of ClusterCraftcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Byzantine-Robust Federated Representation Learningcited by 0