Mesrob I. Ohannessian, PhD, UC San Diego – MIDAS Seminar Series

Mesrob I. Ohannessian, PhD

Postdoctoral Researcher

University of California, San Diego

“Computation-Statistics Tradeoffs in Unsupervised Learning via Data Summarization”

Abstract: Faced with massive data, is it possible to trade off statistical risk and computational time? This challenge lies at the heart of large-scale machine learning. I will show in this talk that we can indeed achieve such risk-time tradeoffs by strategically summarizing the data, in the unsupervised learning problem of probabilistic k-means, i.e. vector quantization. In particular, there exist levels of summarization for which as the data size increases, the running time decreases, while a given risk is maintained. Furthermore, there exists a constructive algorithm that provably finds such tradeoff levels. The summarization in question is based on coreset constructions from computational geometry. I will also show that these tradeoffs exist and may be harnessed for a wide range of real data. This adds data summarization to the list of methods, including stochastic optimization, that allow us to perceive data as a resource rather than an impediment.

Bio: Mesrob I. Ohannessian is a postdoctoral researcher at UC San Diego. Previously, he spent two years in France, one at the Microsoft Research – Inria joint centre as a postdoc, and another at Université Paris-Sud as a Marie Curie Fellow under an ERCIM Alain Bensoussan Fellowship. He received his PhD in Electrical Engineering and Computer Science from MIT. His research interests are broadly in statistics, information theory, machine learning, and their applications, particularly to problems marked by data scarcity.

Light refreshments at 5:00 pm.

For more information on MIDAS or the Seminar Series, please contact midas-contact@umich.edu.

MIDAS gratefully acknowledges Northrop Grumman Corporation for its generous support of the MIDAS Seminar Series.