University of Cambridge > Talks.cam > Statistics > Faster log-concave sampling via algorithmic warm starts

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Faster log-concave sampling via algorithmic warm starts

Download to your calendar using vCal

If you have a question about this talk, please contact Qingyuan Zhao .

The problem of sampling from a log-concave distribution is a key algorithmic component of fields such as Bayesian inference, yet non-asymptotic computational guarantees for this task have only emerged recently, within the last decade. In this talk, I’ll discuss recent progress on understanding one of the most popular samplers, the Metropolis-adjusted Langevin algorithm (MALA), by first showing refined mixing time bounds under a warm start, and then showing how to algorithmically obtain the warm start via the underdamped Langevin process.

This talk is part of the Statistics series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Cambridge Global Health Lecture Series Webinar & SS03, Computer Laboratory, William Gates Building. Museum of Zoology

Other talks

Group Work Title TBC John Kendrew Lecture - Title TBC External Seminar - Hilde Nelissen TBC Differences between Robin and Neumann eigenvalues Group Work
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity