# Optimization or Architecture: How to Hack Kalman Filtering

arXiv: https://arxiv.org/abs/2310.00675 · HTML: https://mlsanity.com/paper/2310.00675/

## 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 (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization](https://mlsanity.com/paper/1708.01885/) (2017)
- [A systematic literature review on state-of-the-art deep learning methods for process prediction](https://mlsanity.com/paper/2101.09320/) (2021)
- [Fitting a Kalman Smoother to Data](https://mlsanity.com/paper/1910.08615/) (2019)
- [Adam revisited: a weighted past gradients perspective](https://mlsanity.com/paper/2101.00238/) (2021)
- [DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter](https://mlsanity.com/paper/1907.09915/) (2019)
- [Continuous Forecasting via Neural Eigen Decomposition](https://mlsanity.com/paper/2202.00117/) (2022)

## Built on by (most cited first, 8 of 8)

- [Pathspace Kalman Filters with Dynamic Process Uncertainty for Analyzing Time-course Data](https://mlsanity.com/paper/2402.04498/) (2024)
- [DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking](https://mlsanity.com/paper/2505.12340/) (2025)
- [Learning MMSE Filters for OFDM Channel Estimation: Attention Transformer Gains at Linear Inference](https://mlsanity.com/paper/2506.00452/) (2025)
- [Data-Driven Discovery of Interpretable Kalman Filter Variants through Large Language Models and Genetic Programming](https://mlsanity.com/paper/2508.11703/) (2025)
- [The Kalman Evolve: Closing the Gap in Kalman Filtering via Interpretable Algorithm Discovery](https://mlsanity.com/paper/2605.26830/) (2026)
- [Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classification](https://mlsanity.com/paper/2606.02767/) (2026)
- [Structured Noise Adaptation for Sequential Bayesian Filtering with Embedded Latent Transfer Operators](https://mlsanity.com/paper/2606.14195/) (2026)
- [Online Learning via Learned Latent Bayesian Tracking](https://mlsanity.com/paper/2609.31559/) (2026)

## 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.