Sketching for Proving Generalization of Support Vector Machines
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=QhnqwQUOxsI
Kasper Larsen (Aarhus University)
https://simons.berkeley.edu/talks/kasper-larsen-aarhus-university-2023-10-09
Sketching and Algorithm Design
Support Vector Machines (SVMs) are among the most fundamental tools for binary classification. In its simplest formulation, an SVM produces a hyperplane separating two classes of data using the largest possible margin to the data. The focus on maximizing the margin has been well motivated through numerous generalization bounds. In this talk, we revisit and improve the classic generalization bounds in terms of margins. Surprisingly, the main tool used is sketching hyperplanes via the Johnson-Lindenstrauss transform.
Other Videos By Simons Institute for the Theory of Computing
Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Sketching and Algorithm Design
Kasper Larsen