University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Step size control for Newton type MCMC samplers Jonathan Goodman

  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

Step size control for Newton type MCMC samplers Jonathan Goodman

Download to your calendar using vCal

If you have a question about this talk, please contact INI IT .

GCS - Geometry, compatibility and structure preservation in computational differential equations

ABSTRACT : MCMC sampling can use ideas from the optimization community.  Optimization via Newton’s method can fail without line search, even for smooth strictly convex problems.  Affine invariant Newton based MCMC sampling uses a Gaussian proposal based on a quadratic model of the potential using the local gradient and Hessian.  This can fail (conjecture: give a transient Markov chain) even for smooth strictly convex potentials.  We describe a criterion that allows a sequence of proposal distributions from X_n with decreasing “step sizes” until (with probability 1) a proposal is accepted.  “Very detailed balance” allows the whole process to preserve the target distribution.  The method works in experiments but the theory is missing.




This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Evolution and Development Seminar Series djl82's list CJBS, 109 Castle Teaching Room

Other talks

Laser tomography for wide area gas emission spatio-temporal reconstruction Title to be confirmed Talk title TBC Summer Cactus & Succulent Show Title to be confirmed CSAR lecture: Decarbonizing road freight (TBC)
 

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