An Identity for Kernel Ridge Regression
Fedor Zhdanov, Yuri Kalnishkan
TL;DR
This paper presents a mathematical identity linking the online ridge regression loss to the best retrospective regressor, providing insights into its cumulative loss properties.
Contribution
It introduces a novel identity that connects online ridge regression loss with the optimal retrospective regressor, enhancing understanding of its theoretical behavior.
Findings
Derived an identity relating online ridge regression loss to the best retrospective regressor
Obtained corollaries about cumulative loss properties of online ridge regression
Provided theoretical insights into the performance of ridge regression in online settings
Abstract
This paper derives an identity connecting the square loss of ridge regression in on-line mode with the loss of the retrospectively best regressor. Some corollaries about the properties of the cumulative loss of on-line ridge regression are also obtained.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsControl Systems and Identification · Sparse and Compressive Sensing Techniques · Statistical Methods and Inference