Skip to main content
Cornell university
Cornell Statistics and Data Science Cornell Statistics and Data Science
  • About Us

    About Us
    Cornell's Department of Statistics and Data Science offers four programs at the undergraduate and graduate levels. Undergraduates can earn a BA in statistical science, social...

    Welcome to the Department of Statistics and Data Science
    History
    Facilities
    Statistics Graduate Society
    Recently Published Papers
  • Academics

    Academics

    Undergraduate
    PhD
    MPS
    PhD Minor in Data Science
    Courses & Course Enrollment
  • People

    People

    Faculty
    Field Faculty
    PhDs
    Emeritus Faculty
    Academic Staff
    Staff
    Research Areas of Expertise
    Statistical Consultants
  • News and Events

    News and Events

    Events
    News
  • Resources

    Resources

    Professional Societies and Meetings
    Affiliated Groups
    Career Services
    Cornell Statistical Consulting Unit
  • Alumni

    Alumni
    Cornell's Statistics and Data Science degrees prepare students for a wide variety of careers, from academia to industry.  See the After Graduation page for a general overview of...

    Alumni Profiles

Search form

You are here

  1. Home 
  2. Events 
  3. Statistics Seminars

Statistics Seminar Speaker: Andre Wibisono 3/20/2024

Event Layout

Wednesday Mar 20 2024

Statistics Seminar Speaker: Andre Wibisono 3/20/2024

4:15pm @ G01 Biotech
In Statistics Seminars

Andre Wibisono is an assistant professor in the Department of Computer Science at Yale University, with a secondary appointment in the Department of Statistics and Data Science. His research interests are in the design and analysis of algorithms for machine learning, in particular for problems in optimization, sampling, and game theory. He received his BS degrees from MIT; his Masters degrees from MIT and from UC Berkeley; and his PhD in Computer Science from UC Berkeley. Before joining Yale in 2021, he has done postdoctoral research at UW Madison and Georgia Tech.

Talk: On Independent Samples along the Langevin Dynamics and Algorithm

Abstract: Sampling from a probability distribution is a fundamental algorithmic task, and one way to do that is to run a Markov chain. The mixing time of a Markov chain characterizes how long we should run the Markov chain until the random variable converges to the stationary distribution, and it has been well-studied. In this talk, we discuss the “independence time” of a Markov chain, which is how long we should run the Markov chain until the initial and final random variables have small mutual information, which means they are approximately independent. We study this question for two popular Markov chains: the Langevin dynamics in continuous time, and the Unadjusted Langevin Algorithm in discrete time. When the target distribution is strongly log-concave, we prove that the mutual information between the initial and final random variables decreases exponentially fast along both Markov chains. These convergence rates are tight, and lead to an estimate of the independence times which are similar to the mixing time guarantees of these Markov chains. To prove our results, we use strong data processing inequality and the regularity properties of these Markov chains. Based on joint work with Jiaming Liang and Siddharth Mitra, https://arxiv.org/abs/2402.17067.

Event Categories

  • Statistics Seminars
  • Special Events

Image Gallery

A color photo of a man smiling for a photo
  • Home
  • About Us
  • Contact Us
  • Careers
© Cornell University Department of Statistics and Data Science

1198 Comstock Hall, 129 Garden Ave., Ithaca, NY 14853

Social Menu

  • Facebook
  • Twitter
  • YouTube
Cornell Bowers CIS College of Computing and Information Science Cornell CALS ILR School

If you have a disability and are having trouble accessing information on this website or need materials in an alternate format, contact web-accessibility@cornell.edu for assistance.