Michael Weylandt: Convex Clustering: Methods, Theory, Algorithms, and Visualizations скачать в хорошем качестве

Michael Weylandt: Convex Clustering: Methods, Theory, Algorithms, and Visualizations

Michael Weylandt's talk for the Statistical Learning Seminar on January 29, 2021. Abstract: Convex clustering is a promising new approach to the classical problem of clustering, combining strong performance in empirical studies with rigorous theoretical foundations. The past few years have seen a surge of interest in convex clustering and breakthroughs in associated theory and methodology. In this talk, I will review this exciting literature, with a particular focus on novel computational strategies developed to construct dendrograms and interactive visualizations from convex clustering approaches. This talk reflects joint work with Genevera Allen, Yue Hu, George Michailidis, John Nagorski, Mitch Rodenberry, Minjie Wang, and Tianyi Yao.