mlsanityData to 14 Oct 2026

Learning to Distributedly Estimate under Partially Known Dynamics: A Covariance-Agnostic Neural Kalman Consensus Filter

arXiv 2606.28441 ↗First posted 26 Jun 2026cs.LG cs.AI cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Online latent state estimation constitutes a fundamental challenge within the artificial intelligence field, serving as a foundational tool for diverse applications, including sequential decision making, anomaly and change-point detection. In this paper, a novel online distributed sensing framework, where agents collaborate and exchange information to perform latent state estimation, is presented. The proposed estimator combines available partial domain knowledge with the representation capabilities of deep neural networks. In particular, the designed sensing framework incorporates prior estimates, optimized consensus weights, and Kalman-like recursive updates to perform decentralized inference, without relying on knowledge of noise statistics. Extensive experiments on linear, chaotic (Lorenz), and practical wireless tracking environments reveal that the proposed Covariance-Agnostic Neural Kalman Consensus Filter (CA-NKCF) outperforms traditional distributed Kalman and particle filters as well as purely model-free deep neural networks, exhibiting robustness even when the underlying motion and observation models are misspecified. It is also demonstrated that CA-NKCF's performance advantage remains stable across varying noise levels, random communication topologies, latent state dimensions, and observation clutter densities induced by scattering objects in wireless systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 65 references that are in the map. First posted on arXiv 26 Jun 2026.

Builds on

29 of 65 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  6. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
  7. 2015LSTM: A Search Space Odysseycited by 316
  8. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  9. 2015Deep Kalman Filterscited by 166
  10. 2020Model-Based Deep Learningcited by 141
  11. 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 132
  12. 2016Sequential Neural Models with Stochastic Layerscited by 115
17 more
  1. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  2. 2017Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularizationcited by 36
  3. 2019Combining Generative and Discriminative Models for Hybrid Inferencecited by 34
  4. 2021Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detectioncited by 34
  5. 2023DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setupcited by 19
  6. 2023Latent-KalmanNet: Learned Kalman Filtering for Tracking from High-Dimensional Signalscited by 17
  7. 2023Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learningcited by 14
  8. 2021RTSNet: Learning to Smooth in Partially Known State-Space Models (Preprint)cited by 11
  9. 2023A Tutorial on 5G Positioningcited by 6
  10. 2024CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Criticscited by 5
  11. 2025Dual-Balancing for Physics-Informed Neural Networkscited by 5
  12. 2017A Distributed Control Framework for a Team of Unmanned Aerial Vehicles for Dynamic Wildfire Trackingcited by 4
  13. 2025LumiMAS: A Comprehensive Framework for Real-Time Monitoring and Enhanced Observability in Multi-Agent Systemscited by 4
  14. 2025Graph-CNNs for RF Imaging: Learning the Electric Field Integral Equationscited by 3
  15. 2022Distributed Kalman filtering with event-triggered communication: a robust approachcited by 1
  16. 2022Radio Localization and Sensing -- Part I: Fundamentalscited by 1
  17. 2025IMAS2: Joint Agent Selection and Information-Theoretic Coordinated Perception In Dec-POMDPscited by 1

Built on by

Not cited yet.