News & Events
Department Events & Announcements

Events

  • Jun
    1

    CS Colloquium: Zhaoran Wang "Computational and Statistical Efficiency of Policy Optimization"

    Department of Computer Science

    12:00 PM Zoom, Mudd Hall ( formerly Seeley G. Mudd Library)

    EVENT DETAILS

    Livestream:
    https://northwestern.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=7a07cf41-b0cc-4b80-8291-abc9015d4ccb

    Title:
    Computational and Statistical Efficiency of Policy Optimization

    Abstract
    Coupled with powerful function approximators such as neural networks, policy optimization plays a key role in the tremendous empirical successes of deep reinforcement learning. In sharp contrast, the theoretical understandings of policy optimization remain rather limited from both the computational and statistical perspectives. From the perspective of computational efficiency, it remains unclear whether policy optimization converges to the globally optimal policy in a finite number of iterations, even given infinite data. From the perspective of statistical efficiency, it remains unclear how to attain the globally optimal policy with a finite regret or sample complexity.

    To address the computational question, I will show that, under suitable conditions, natural policy gradient/proximal policy optimization/trust-region policy optimization (NPG/PPO/TRPO) converges to the globally optimal policy at a sublinear rate, even when it is coupled with neural networks. To address the statistical question, I will present an optimistic variant of NPG/PPO/TRPO, namely OPPO, which incorporates exploration in a principled manner and attains a \sqrt{T}-regret.

    (Joint work with Qi Cai, Chi Jin, Jason Lee, Boyi Liu, Zhuoran Yang)

    Biography
    Zhaoran Wang is an assistant professor at Northwestern IEMS, working at the interface of machine learning, statistics, and optimization. He is the recipient of the AISTATS (Artificial Intelligence and Statistics Conference) notable paper award, ASA (American Statistical Association) best student paper in statistical learning and data mining, INFORMS (Institute for Operations Research and the Management Sciences) best student paper finalist in data mining, and the Microsoft fellowship.

    more less

    TIME Monday, June 1, 2020 at 12:00 PM - 1:00 PM

    LOCATION Zoom, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

    ADD TO CALENDAR SHARE

    CONTACT Pam Villalovoz    pmv@northwestern.edu EMAIL

    CALENDAR Department of Computer Science

  • Jul
    21

    CS+X Colloquium hosted by Latin@CS, Leonardo Neves "Research at Snapchat: How long-term investments in innovation can help companies succeed"

    Department of Computer Science

    4:00 PM Zoom, Mudd Hall ( formerly Seeley G. Mudd Library)

    EVENT DETAILS

    TIME Tuesday, July 21, 2020 at 4:00 PM - 5:00 PM

    LOCATION Zoom, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

    ADD TO CALENDAR SHARE

    CONTACT Pam Villalovoz    pmv@northwestern.edu EMAIL

    CALENDAR Department of Computer Science