Logo: University of Southern California

Events Calendar

Select a calendar:

Filter March Events by Event Type:

Events for March 08, 2018

  • CS Colloquium: Jonas Mueller (MIT) – Learning Optimal Interventions under Uncertainty

    Thu, Mar 08, 2018 @ 11:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    Conferences, Lectures, & Seminars

    Speaker: Jonas Mueller, MIT

    Talk Title: Learning Optimal Interventions under Uncertainty

    Series: Computer Science Colloquium

    Abstract: A basic goal of data analysis is learning which actions (ie. interventions) are best for producing desired outcomes. While advances in reinforcement learning and bandit/Bayesian optimization have shown great promise, these sequential methods are primarily limited to digital environments where iterating between modeling and experimentation is easy. Although more widely applicable, learning from a fixed (observational) dataset will inherently involve substantial uncertainty due to limited samples, and it is undesirable to prescribe actions whose outcomes are unclear.

    In this talk, I will consider such settings from a Bayesian perspective and formalize the of role of uncertainty in data-driven actions. Adopting a Gaussian process framework, I will introduce a conservative definition of the optimal intervention which can be either tailored on an individual basis or globally enacted over a population. Subsequently, these ideas are extended to structured sequence data via a recurrent variational autoencoder model. In both cases, gradient methods are employed to identify the best intervention and a key theme of the approach is carefully constraining this optimization to avoid regions of high uncertainty. Various applications of this methodology will presented including gene expression manipulation, therapeutic antibody design, and revision of natural language.

    This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity in OHE 100D, seats will be first come first serve.

    Biography: Jonas Mueller is a Computer Science Ph.D. student at MIT working with Tommi Jaakkola and David Gifford. His research interests lie in developing machine learning methods to advance both statistical science and artificial intelligence applications. Integrating ideas from optimal transport, deep learning, Bayesian/bandit optimization, and interpretable modeling, much of his work has been motivated by applications in bioinformatics and natural language processing. Previously, Jonas studied Math and Statistics at UC Berkeley, where he was awarded the Departmental Citation, and he recently also spent some time at Microsoft Research.

    Host: Computer Science Department

    Location: Olin Hall of Engineering (OHE) - 100D

    Audiences: Everyone Is Invited

    Contact: Computer Science Department

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Biomedical Engineering Department Guest Speaker

    Thu, Mar 08, 2018 @ 11:00 AM - 12:00 PM

    Alfred E. Mann Department of Biomedical Engineering

    Conferences, Lectures, & Seminars


    Talk Title: How does the brain control dexterous hand function (and how does function recover after injury)

    Abstract: It is hard to over-state the importance of our hands in daily life; they are the primary means with which we manipulate the environment around us. Evidence from invasive studies in non-human primates has demonstrated that hand function is controlled by interactions between motor circuits in cortical and subcortical brain areas. Since such invasive investigations in humans are not possible, the question of how cortical brain areas organize to facilitate dexterous control, and the extent to which (if at all) subcortical pathways contribute to hand function in man is unknown. In this seminar, I will draw upon multiple studies from my research program to answer these two questions. First, I will use functional magnetic resonance imaging to characterize the population response of neurons in the neocortex that are critical for dexterous hand control. I will provide evidence that the population response appears to be shaped by experiential use of the hand, and will further demonstrate the nature of plasticity in the associated circuits by using individuals with hand amputation as a model of neocortical deafferentation. Next, I will discuss evidence for a new model of hand recovery after stroke, one that relies on the ability of subcortical brain structures to provide compensatory control of the hand after damage to the neocortex. Throughout the seminar, I will briefly highlight how my research program provides tools that can be used to investigate hand function as a function of development, ageing, and disease, as well as provide hints on how to recover dexterous control in patients after neural injuries (e.g. stroke, cervical spondylotic myelopathy).

    Host: Francisco Valero-Cuevas, PhD

    Location: DRB 145/145A

    Audiences: Everyone Is Invited

    Contact: Mischalgrace Diasanta

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • EE Seminar - Bridging Control Theory and Machine Learning

    Thu, Mar 08, 2018 @ 03:00 PM - 04:00 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars

    Speaker: Dr. Bin Hu, Postdoctoral Researcher, University of Wisconsin-Madison

    Talk Title: Bridging Control Theory and Machine Learning

    Abstract: The design of modern intelligent systems relies heavily on techniques developed in the control and machine learning communities. On one hand, control techniques are crucial for safety-critical systems; the robustness to uncertainty and disturbance is typically introduced by a model-based design equipped with sensing, actuation, and feedback. On the other hand, learning techniques have achieved the state-of-the-art performance for a variety of artificial intelligence tasks (computer vision, natural language processing, and Go). The developments of next-generation intelligent systems such as self-driving cars, advanced robotics, and smart buildings require leveraging these control and learning techniques in an efficient and safe manner.

    This talk will focus on fundamental connections between robust control and machine learning. Specifically, we will present a control perspective on the empirical risk minimization (ERM) problem in machine learning. ERM is a central topic in machine learning research, and is typically solved using first-order optimization methods which are developed in a case-by-case manner. First, we will discuss how to adapt robust control theory to automate the analysis of such optimization methods including the gradient descent method, Nesterov's accelerated method, stochastic gradient descent (SGD), stochastic average gradient (SAG), SAGA, Finito, stochastic dual coordinate ascent (SDCA), stochastic variance reduction gradient (SVRG), and Katyusha momentum. Next, we will show how to apply classical control design tools (Nyquist plots and multiplier theory) to develop new robust accelerated methods for ERM problems. Finally, we will conclude with some long-term research vision on the general connections between our proposed control-oriented tools and reinforcement learning methods.

    Biography: Bin Hu received the B.Sc. in Theoretical and Applied Mechanics from the University of Science and Technology of China in 2008, and received the M.S. in Computational Mechanics from Carnegie Mellon University in 2010. He received the Ph.D. in Aerospace Engineering and Mechanics at the University of Minnesota in 2016, advised by Peter Seiler. He is currently a postdoctoral researcher in the optimization group of the Wisconsin Institute for Discovery at the University of Wisconsin-Madison. He is interested in building fundamental connections between the techniques used in the control and machine learning communities. His current research focuses on tailoring robust control theory (integral quadratic constraints, dissipation inequalities, jump system theory, etc) to automate the analysis and design of stochastic optimization methods for large-scale learning tasks. He is also particularly interested in the connections between model-based control and model-free reinforcement learning.

    Host: Ashutosh Nayyar, ashutosn@usc.edu, x02353

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

    Audiences: Everyone Is Invited

    Contact: Mayumi Thrasher

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • Viterbi Career Gateway Workshop

    Thu, Mar 08, 2018 @ 04:00 PM - 05:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions

    Take part in a live tutorial to help you navigate Viterbi Career Gateway, a powerful job & internship search tool available ONLY to Viterbi students.

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

    Audiences: All Viterbi

    Contact: RTH 218 Viterbi Career Connections

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File