[Theory Seminar] Vaggos Chatziafratis (Northwestern Unviersity) - Hierarchical Clustering: Recent Progress and Open Questions
Thu, Dec 02, 2021 @ 10:30 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Vaggos Chatziafratis, Northwestern University
Talk Title: Hierarchical Clustering: Recent Progress and Open Questions
Abstract: Hierarchical Clustering is an important tool for unsupervised learning whose goal is to construct a hierarchical decomposition of a given dataset describing relationships at all levels of granularity simultaneously. Despite its long history, Hierarchical Clustering was underdeveloped from a theoretical perspective, partly because of a lack of suitable objectives and algorithms with guarantees. In this talk, I want to tell you about the recent progress in the area with an emphasis on approximation algorithms and hardness results, and also highlight some interesting open problems.
Biography: Vaggos Chatziafratis\' primary interests are in Algorithms and Machine Learning Theory. He is currently a postdoc at Northwestern and he will be a FODSI fellow at MIT and Northeastern starting January. He will also be joining UC Santa Cruz in Fall 2022 as an Assistant Professor.
Before that, he was at Google Research in New York, where he was part of the Algorithms and Graph Mining teams. Prior to that, he received his Ph.D. in Computer Science at Stanford, advised by Tim Roughgarden and co-advised by Moses Charikar. He received a Diploma in EECS from the National Technical University of Athens, Greece.
Host: Curtis Bechtel
Audiences: Everyone Is Invited
Contact: Assistant to CS chair