Logo: University of Southern California

Events Calendar



Select a calendar:



Filter December Events by Event Type:


SUNMONTUEWEDTHUFRISAT

Conferences, Lectures, & Seminars
Events for December

  • Data-Driven Control

    Wed, Dec 05, 2018 @ 12:00 PM - 01:00 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Paulo Tabuada, University of California Los Angeles

    Talk Title: Data-Driven Control

    Series: Center for Cyber-Physical Systems and Internet of Things

    Abstract: More than a decade ago Fliess and co-workers proposed model-free control as a possible answer to the inherent difficulties in controlling non-linear systems. Their key insight was that by using a sufficiently high sampling rate we can use a simple linear model for control purposes thereby trivializing nonlinear controller design. Although controllers based on linear approximations of nonlinear systems are ubiquitous in industry, providing formal guarantees for such designs has remained a challenge. In this talk we re-interpret Fliess work as data-driven control and identify a set of assumptions enabling us to mathematically prove that a model is not necessary to control non-linear systems. We illustrate the usefulness and applicability of the results via experimental results and conclude by speculating about the right mix of model-based and data-driven design in the context of Cyber-Physical Systems.

    Biography: Paulo Tabuada was born in Lisbon, Portugal, one year after the Carnation Revolution. He received his "Licenciatura" degree in Aerospace Engineering from Instituto Superior Tecnico, Lisbon, Portugal in 1998 and his Ph.D. degree in Electrical and Computer Engineering in 2002 from the Institute for Systems and Robotics, a private research institute associated with Instituto Superior Tecnico. Between January 2002 and July 2003 he was a postdoctoral researcher at the University of Pennsylvania. After spending three years at the University of Notre Dame, as an Assistant Professor, he joined the Electrical Engineering Department at the University of California, Los Angeles, where he established and directs the Cyber-Physical Systems Laboratory. Paulo Tabuada's contributions to cyber-physical systems have been recognized by multiple awards including the NSF CAREER award in 2005, the Donald P. Eckman award in 2009 and the George S. Axelby award in 2011. In 2009 he co-chaired the International Conference Hybrid Systems: Computation and Control (HSCC'09) and in he was program co-chair for the 3rd IFAC Workshop on Distributed Estimation and Control in Networked Systems (NecSys'12). He currently serves as associate editor for the IEEE Transactions on Automatic Control and his latest book, on verification and control of hybrid systems, was published by Springer in 2009.

    Host: Paul Bogdan

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

    Audiences: Everyone Is Invited

    Contact: Talyia White

    OutlookiCal
  • BME seminars

    Fri, Dec 07, 2018 @ 11:00 AM - 12:00 PM

    Alfred E. Mann Department of Biomedical Engineering

    Conferences, Lectures, & Seminars


    Speaker: Hana El-Samad, Professor and Vice Chair Department of Biochemistry and Biophysics Chan-Zuckerberg Biohub University of California, San Francisco

    Talk Title: Untangling the Feedback Loops

    Series: Biomedical Engineering Special Seminar

    Abstract: Organisms are an evolutionary masterpiece of feedback control, featuring a mind boggling capacity to self-correct. Feedback loops enable cells to grow and then stop at the right size, to divide and self-repair, and to respond with agility to their changing environment. Individual cells engage in long range extracellular feedback with other cells, ensuring continued homeostasis of communities, tissues and organs. . In this talk, we demonstrate the dynamic anatomy of a few feedback loops and highlight the technological advances that made these insights possible.

    Host: Stacey Finley

    More Information: hana el samad flier (00000002).pdf

    Location: Corwin D. Denney Research Center (DRB) - 145A

    Audiences: Everyone Is Invited

    Contact: Mischalgrace Diasanta

    OutlookiCal
  • Zap Meets Momentum: New Stochastic Approximation Algorithms and Applications to Reinforcement Learning

    Wed, Dec 12, 2018 @ 12:00 PM - 01:00 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Adithya Devaraj, University of Florida

    Talk Title: Zap Meets Momentum: New Stochastic Approximation Algorithms and Applications to Reinforcement Learning

    Series: Center for Cyber-Physical Systems and Internet of Things

    Abstract: Stochastic approximation algorithms are used to approximate solutions to fixed point equations that involve expectations of functions with respect to possibly unknown distributions. Among many algorithms in machine learning, reinforcement learning algorithms such as TD- and Q-learning are two of its most famous applications.

    This talk will provide an overview of stochastic approximation, with focus on optimizing the rate of convergence. Based on this general theory, the well known slow convergence of Q-learning is explained: the variance of the algorithm is typically infinite.

    Three new Q-learning algorithms are introduced to dramatically improve performance:

    (i) The Zap Q-learning algorithm that has provably optimal asymptotic variance, and resembles the Newton-Raphson method in a deterministic setting
    (ii) The PolSA algorithm that is based on Polyak's momentum technique, but with a specialized matrix momentum, and
    (iii) The NeSA algorithm based on Nesterov's acceleration technique

    Analysis of (ii) and (iii) require entirely new analytic techniques. One approach is via coupling: conditions are established under which the parameter estimates obtained using the PolSA algorithm couple with those obtained using the Newton-Raphson based algorithm. Numerical examples confirm this behavior and the remarkable performance of these algorithms.


    Biography: Adithya Devaraj is a Ph.D. student at the University of Florida where he works with Prof. Sean Meyn. The focus of his research has been variance reduction in stochastic approximation algorithms with application to reinforcement learning. He has held visiting/research positions at the Indian Institute of Science, Bangalore, Inria, Paris, and the Simons Institute for the Theory of Computing at UC Berkeley.

    Host: Rahul Jain

    Location: Ronald Tutor Hall of Engineering (RTH) - 105

    Audiences: Everyone Is Invited

    Contact: Talyia White

    OutlookiCal
  • Astani Civil and Environmental Engineering Seminar

    Thu, Dec 13, 2018 @ 03:00 PM - 04:00 PM

    Sonny Astani Department of Civil and Environmental Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dr. Kartik Chandran , Columbia University

    Talk Title: Emerging Models in Carbon and Nitrogen Cycling

    Abstract: See Attachment.

    Host: Dr. Adam Smith

    More Information: Kartik Chandran Announcement.pdf

    Location: Ronald Tutor Hall of Engineering (RTH) - 211

    Audiences: Everyone Is Invited

    Contact: Evangeline Reyes

    OutlookiCal