Campus Event Calendar
Event Entry
What and Who
Inexactness, geometry, and optimization for data analysis
Suvrit Sra
Max-Planck Institute for Intelligent Systems, Tübingen, and Carnegie Mellon University (ML Dept), Pittsburgh
Talk
Suvrit Sra is a Sr. Research Scientist at the Max Planck Institute
for Intelligent Systems, in Tübingen, Germany. He obtained Ph.D. in
Computer Science from the University of Texas at Austin in 2007. In
Spring 2013 he was visiting faculty at UC Berkeley (EECS), and is
currently also a visiting faculty member in the Machine Learning
Department at Carnegie Mellon University.
His research is dedicated to bridging a number of mathematical areas
(such as geometry, analysis, noncommutative algebra, convex
analysis, matrix analysis, statistics, optimization, etc.) with
data-driven real-world applications.
His work has won several awards; most notably the "SIAM 2011
Outstanding Paper Prize". He regularly organizes a workshops on
"Optimization for Machine Learning" at the Neural Information
Processing Systems (NIPS) conference, and has recently (co)-edited a
book with the same title.
AG 1, AG 2, AG 3, AG 4, AG 5, RG1, SWS, MMCI
MPI Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Wednesday, 9 April 2014
14:00
30 Minutes
E1 4
024
Saarbrücken
Abstract
The current data-age is witnessing an unprecedented confluence of
disciplines. A single data analysis task can demand expertise in
computer science, statistics, functional analysis, optimization, or
more. But what aspects of data are driving this rich interaction? We
may single out at least two: size and form.
We hear a lot about "size" but less about "form". I will highlight
examples from my own research that touch both these aspects. In
particular, I mention progress on a framework for inexact
optimization, which subsumes numerous other algorithms and is first
of its kind for tackling nonconvex, nonsmooth problems that arise in
large-scale data analysis. Next, I will talk more about "form",
specifically the geometry of data. My motivation lies in a number of
applications where data are not merely vectors, but richer objects
such as matrices, strings, functions, graphs, trees, etc. Processing
such data in their "intrinsic representation" raises deep
mathematical and algorithmic concerns replete with open problems.
To add perspective, I ground the whole talk in applications from
computational imaging, computer vision, machine learning, and
statistics. Time permitting, I will mention some fascinating
connections of beyond machine learning and data analysis.
disciplines. A single data analysis task can demand expertise in
computer science, statistics, functional analysis, optimization, or
more. But what aspects of data are driving this rich interaction? We
may single out at least two: size and form.
We hear a lot about "size" but less about "form". I will highlight
examples from my own research that touch both these aspects. In
particular, I mention progress on a framework for inexact
optimization, which subsumes numerous other algorithms and is first
of its kind for tackling nonconvex, nonsmooth problems that arise in
large-scale data analysis. Next, I will talk more about "form",
specifically the geometry of data. My motivation lies in a number of
applications where data are not merely vectors, but richer objects
such as matrices, strings, functions, graphs, trees, etc. Processing
such data in their "intrinsic representation" raises deep
mathematical and algorithmic concerns replete with open problems.
To add perspective, I ground the whole talk in applications from
computational imaging, computer vision, machine learning, and
statistics. Time permitting, I will mention some fascinating
connections of beyond machine learning and data analysis.
Contact
Bernt Schiele
--email hidden
passcode not visible
logged in users only
Bernt Schiele, 04/07/2014 14:12 -- Created document.