[Colloquium] DATE CORRECTION FOR BYRON BOOTS

[Dawn Ellis]

When:     MONDAY, March 17th at 11am

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room #526

Speaker:  Byron Boots, University of Washington

Title:       Machine Learning For Modeling Real-World Dynamical Systems

Abstract:

A major challenge in machine learning is to reliably and automatically
discover hidden structure in high-dimensional data. This is an especially
formidable problem for sequential data: revealing the dynamical system that
governs a complex time series is often not just difficult, but provably
intractable. Popular maximum likelihood strategies for learning dynamical
system models are slow in practice and often get stuck at poor local
optima, problems that greatly limit the utility of these techniques when
learning from real-world data. Although these drawbacks were long thought
to be unavoidable, recent work has shown that progress can be made by
shifting the focus of learning to realistic instances that rule out the
intractable cases.

In this talk, I will present a new family of computational approaches for
learning dynamical system models. The key insight is that low-order moments
of observed data often possess structure that can be revealed by powerful
spectral decomposition methods, and, from this structure, model parameters
can be directly recovered. Based on this insight, we design highly
effective algorithms for learning parametric models like Kalman Filters and
Hidden Markov Models, as well as an expressive new class of nonparametric
models via reproducing kernels. Unlike maximum likelihood-based approaches,
these new learning algorithms are statistically consistent, computationally
efficient, and easy to implement using established matrix-algebra
techniques. The result is a powerful framework for learning dynamical
system models with state-of-the-art performance on video, robotics, and
biological modeling problems.

Bio:
Byron Boots is a postdoctoral researcher working with Dieter Fox in the
Robotics and State Estimation Lab at the University of Washington. He
received his Ph.D. in Machine Learning from Carnegie Mellon University in
2012 where he was advised by Geoffrey Gordon. Byron's work on learning
models of dynamical systems received the 2010 Best Paper award at the
International Conference on Machine Learning (ICML-2010). His research
focuses on modeling and control problems at the intersection of statistical
machine learning, artificial intelligence, and robotics.

Host:  Greg Shakhnarovich, greg at ttic.edu


-- 
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu

TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637



-- 
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu

TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20140314/d1e7c5e0/attachment.htm