University of Cambridge > Talks.cam > Statistics > Entropy contraction of the Gibbs sampler under log-concavity

  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

Entropy contraction of the Gibbs sampler under log-concavity

Download to your calendar using vCal

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

In this talk I will present recent work (https://arxiv.org/abs/2410.00858) on the non-asymptotic analysis of the Gibbs sampler, which is a canonical and popular Markov chain Monte Carlo algorithm for sampling. In particular, under the assumption that the probability measure Ī€ of interest is strongly log-concave, we show that the random scan Gibbs sampler contracts in relative entropy and provide a sharp characterization of the associated contraction rate. The result implies that, under appropriate conditions, the number of full evaluations of Ī€ required for the Gibbs sampler to converge is independent of the dimension. If time permits, I will also discuss connections and applications of the above results to the problem of zero-order parallel sampling.

Based on joint work with Filippo Ascolani and Hugo Lavenant.

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

Institute of Criminology English Faculty Room GR05 Computer Laboratory, William Gates Building, Room FW26

Other talks

Non-stationarity in structural dynamics, challenges and implications for modelling and structural health monitoring Title TBC A Novel Diffusion Model based Approach for Sleep Music Generation Decoding genomic chaos - a pancancer compendium of chromosomal instability Title to be confirmed External Seminar - Jenn Brophy TBC
 

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