Multi-class classification: mirror descent approach
Daria Reshetova
TL;DR
This paper introduces a stochastic mirror descent algorithm for multi-class classification, providing theoretical risk bounds and examples of geometries that enhance efficiency in error reduction.
Contribution
It develops a novel stochastic mirror descent approach for multi-class classification with theoretical risk bounds and geometric insights for improved efficiency.
Findings
Derived risk bounds for the proposed algorithm
Identified set geometries that improve efficiency
Demonstrated effectiveness in multi-class classification
Abstract
We consider the problem of multi-class classification and a stochastic opti- mization approach to it. We derive risk bounds for stochastic mirror descent algorithm and provide examples of set geometries that make the use of the algorithm efficient in terms of error in k.
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
TopicsFace and Expression Recognition · Digital Imaging for Blood Diseases