CMStatistics 2022: Start Registration
View Submission - CMStatistics
Title: Robust spectral clustering with rank statistics Authors:  Joshua Cape - University of Wisconsin, Madison (United States) [presenting]
Abstract: Traditional non-robust approaches for spectral clustering and embedding exhibit severe performance degradation in the presence of outliers, heavy-tailed distributions, and heterogeneous noise variances. In this talk, we address these challenges by studying the problem of robust spectral clustering using rank statistics. We highlight ongoing work spanning methodology, theory, and applications, with a focus on statistical guarantees for user-friendly dimensionality reduction techniques.