Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 497 - Variable Selection
Type: Contributed
Date/Time: Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #313642
Title: Simultaneous Outlier Detection and Feature Selection Using Mixed-Integer Programming
Author(s): Ana Kenney* and Luca Insolia and Francesca Chiaromonte and Giovanni Felici
Companies: Pennsylvania State University and Scuola Normale Superiore (Pisa Italy) and Pennsylvania State University and Sant’Anna School of Advanced Studies (Pisa Italy) and IIASI CNR
Keywords: Sparse Estimatioin; Mixed-Integer Programming; Outlier Detection; Feature Selection

We study high-dimensional regression models contaminated by multiple mean-shift outliers affecting both the response and some of the predictors. Under a sparsity assumption, we propose the use of Mixed-Integer Programming techniques to simultaneously perform feature selection and outlier detection. We prove theoretical properties of this approach and show its superior performance than competing methods in an extensive simulation study and a real data application.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program