Summary of Outlier-robust Kalman Filtering Through Generalised Bayes, by Gerardo Duran-martin et al.
Outlier-robust Kalman Filtering through Generalised Bayes
by Gerardo Duran-Martin, Matias Altamirano, Alexander Y. Shestopaloff, Leandro Sánchez-Betancourt, Jeremias Knoblauch, Matt Jones, François-Xavier Briol, Kevin Murphy
First submitted to arxiv on: 9 May 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Systems and Control (eess.SY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel Bayesian update rule for online filtering in state-space models that is robust to outliers and misspecified measurement models. The method combines generalized Bayesian inference with filtering techniques like the extended Kalman filter and ensemble Kalman filter. It demonstrates robustness through generalized Bayesian inference and computational efficiency through the extended Kalman filter, even in nonlinear models. This approach matches or outperforms other robust filtering methods at a significantly lower computational cost. The paper showcases its effectiveness on various filtering problems, including object tracking, high-dimensional chaotic systems, and online learning of neural networks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research develops a new way to improve the accuracy of online filters in complex systems. It creates a special rule for updating information that works well even when there are mistakes or unusual data points. This rule combines two existing methods to make it both accurate and efficient. The scientists tested their approach on several different problems, including tracking objects, understanding chaotic systems, and learning neural networks. Their method performed well and was often better than other similar approaches. |
Keywords
» Artificial intelligence » Bayesian inference » Object tracking » Online learning » Tracking
