mlsanityData to 14 Oct 2026

Optimization or Architecture: How to Hack Kalman Filtering

arXiv 2310.00675 ↗First posted 1 Oct 2023cs.LG eess.SPcited by 8

Not on the map. Why?

Abstract (arXiv)

In non-linear filtering, it is traditional to compare non-linear architectures such as neural networks to the standard linear Kalman Filter (KF). We observe that this mixes the evaluation of two separate components: the non-linear architecture, and the parameters optimization method. In particular, the non-linear model is often optimized, whereas the reference KF model is not. We argue that both should be optimized similarly, and to that end present the Optimized KF (OKF). We demonstrate that the KF may become competitive to neural models - if optimized using OKF. This implies that experimental conclusions of certain previous studies were derived from a flawed process. The advantage of OKF over the standard KF is further studied theoretically and empirically, in a variety of problems. Conveniently, OKF can replace the KF in real-world systems by merely updating the parameters.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 11 of its 54 references that are in the map. First posted on arXiv 1 Oct 2023.

Builds on

11 of 54 references.

References · 11

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  4. 2020MOT20: A benchmark for multi object tracking in crowded scenescited by 357
  5. 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 132
  6. 2017Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularizationcited by 36
  7. 2021A systematic literature review on state-of-the-art deep learning methods for process predictioncited by 32
  8. 2019Fitting a Kalman Smoother to Datacited by 9
  9. 2021Adam revisited: a weighted past gradients perspectivecited by 9
  10. 2019DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Cluttercited by 5
  11. 2022Continuous Forecasting via Neural Eigen Decompositioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 4.

8 papers.

  1. 2024Pathspace Kalman Filters with Dynamic Process Uncertainty for Analyzing Time-course Datacited by 0
  2. 2025DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Trackingcited by 0
  3. 2025Learning MMSE Filters for OFDM Channel Estimation: Attention Transformer Gains at Linear Inferencecited by 0
  4. 2025Data-Driven Discovery of Interpretable Kalman Filter Variants through Large Language Models and Genetic Programmingcited by 0
  5. 2026The Kalman Evolve: Closing the Gap in Kalman Filtering via Interpretable Algorithm Discoverycited by 0
  6. 2026Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classificationcited by 0
  7. 2026Structured Noise Adaptation for Sequential Bayesian Filtering with Embedded Latent Transfer Operatorscited by 0
  8. 2026Online Learning via Learned Latent Bayesian Trackingcited by 0