Stay Informed:
Baskin Engineering COVID-19 Information and Resources
Campus Roadmap to Recovery
Zoom Links: Zoom Help | Teaching with Zoom | Zoom Quick Guide

From Darwin to Deep Learning: A Tale of Algorithms, Optimization and Chaos

Speaker Name: 
Evangelos (Vaggos) Chatziafratis
Speaker Title: 
Visiting Faculty Researcher
Speaker Organization: 
Google Research New York
Start Time: 
Thursday, March 4, 2021 - 11:00am
End Time: 
Thursday, March 4, 2021 - 12:15pm
Via Zoom Link
Seshadhri Comandur


In this talk, we shed new light on two basic questions in machine learning using ideas from approximation algorithms, optimization and dynamical systems. 

The first question concerns a popular tool in unsupervised learning that partitions a dataset in a hierarchical manner, called Hierarchical Clustering. Despite its long history and plethora of heuristics, a principled framework for understanding its optimization properties had been missing. Our work takes a formal approach and puts Hierarchical Clustering on a firm theoretical grounding, highlighting new connections to convex optimization and graph algorithms. 

The second question concerns the benefits of depth in neural networks. A crucial element in the success of deep learning is the deployment of progressively deeper networks, but is there a mathematical explanation behind this phenomenon? Introducing new ideas from discrete dynamical systems, we present depth vs width tradeoffs, showing that for certain tasks, depth can be exponentially more important than width.



Vaggos Chatziafratis’ primary interests are in Algorithms and Machine Learning Theory. He is currently a Visiting Faculty Researcher at Google Research in New York, hosted by Mohammad Mahdian and Vahab Mirrokni, where he is part of the Algorithms and Graph Mining teams. Prior to that, he received his Ph.D. in Computer Science at Stanford (June 2020), where he was part of the Theory group, advised by Tim Roughgarden and co-advised by Moses Charikar. His PhD thesis was on algorithms and their limitations for Hierarchical Clustering. Prior to Stanford, he received a Diploma in EECS from the National Technical University of Athens, Greece.


Zoom Link:

Event Type: