Speaker: Professor Julio López
Instituto de Ciencias Básicas, Universidad Diego Portales, Santiago, Chile
Date: September 08, 2021 at 09:30 am (Chilean-time)
Title: Regularized version of the minimax probability machine
Abstract: In this talk we present novel second-order cone programming formulations for binary classification, by extending the Minimax Probability Machine (MPM) approach. Inspired by Support Vector Machines, a regularization term is included in the MPM and Minimum Error Minimax Probability Machine methods. This inclusion reduces the risk of obtaining ill-posed estimators, stabilizing the problem, and, therefore, improving the generalization performance. Our approaches are first derived as linear methods, and subsequently extended as kernel-based strategies for nonlinear classification. Experiments on well-known binary classification datasets demonstrate the virtues of the regularized formulations in terms of predictive performance.
A recorded video of the conference is …. ; the slides can be downloaded …
Venue: Online via Google Meet: https://meet.google.com/gjq-cwic-udo
A brief biography of the speaker: Julio López is an Associate Professor at the Institute of Basic Sciences, University Diego Portales, Santiago, Chile. He obtained his PhD degree at the University of Chile, in 2009. His research interests include conic programming, convex analysis, algorithms, and machine learning.
Coordinators: Fabián Flores-Bazán (CMM, Universidad de Concepción) and Abderrahim Hantoute (Alicante)