LearnIng, Optimization, and DecisioN Systems (LIONS)

Massive data poses a fundamental challenge to learning algorithms, which is captured by the following computational dogma: the running time of an algorithm increases with the size of its input data. The available computational power, however, is growing slowly relative to data sizes. Hence, large-scale machine learning problems of interest require increasingly more time to solve.

Our research demonstrates that this dogma is false in general, and supports an emerging perspective in computation: data should be treated as a resource that can be traded off with other resources, such as running time. For data acquisition and communications, we have also shown related sampling, energy, and circuit area trade-offs.

This talk will summarize our work confronting these challenges by building on the new mathematical foundations on how we generate data via sampling, how we set up learning objectives that govern our fundamental goals, and how we optimize these goals to obtain solutions and to make optimal decisions. We then demonstrate task-specific, end-to-end trade-offs (e.g., samples, power, computation, storage, and statistical precision) in broad domains, by not only with our recently built, low-power analog-to-information conversion hardware for neural signal acquisition, but also accelerating magnetic resonance imaging, and engineering new decision tools for discovery in machine learning.
 
Program

-Introduction by Giovanni de Micheli, Director of the Institute of Electrical Engineering and of the Centre of Integrated Systems
-Inaugural lecture of Prof. Volkan Cevher, "LearnIng, Optimization, and DecisioN Systems (LIONS)"

Registration is required: http://go.epfl.ch/cevher

Bio:
Volkan Cevher received the B.Sc. (valedictorian) in electrical engineering from Bilkent University in Ankara, Turkey, in 1999 and the Ph.D. in electrical and computer engineering from the Georgia Institute of Technology in Atlanta, GA in 2005. He was a Research Scientist with the University of Maryland, College Park from 2006-2007 and also with Rice University in Houston, TX, from 2008-2009. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University. His research interests include signal processing theory, machine learning, convex optimization, and information theory. Dr. Cevher was the recipient of the IEEE Signal Processing Society Best Paper Award in 2016, a Best Paper Award at CAMSAP in 2015, a Best Paper Award at SPARS in 2009, and an ERC CG in 2016 as well as an ERC StG in 2011.