Convergence Bounds for the Random Walk Metropolis Algorithm - Perspectives from Isoperimetry

Add to your list(s) Download to your calendar using vCal

• Sam Power (University of Bristol)
• Monday 25 November 2024, 13:30-14:20
• Seminar Room 1, Newton Institute.

If you have a question about this talk, please contact nobody.

SSDW04 - Monte Carlo sampling: beyond the diffusive regime

The Random Walk Metropolis (RWM) is a simple and enduring Markov chain-based algorithm for approximate simulation from an intractable ‘target’ probability distribution. In a pair of recent works, we have undertaken a detailed study of the quantitative convergence of this algorithm to its equilibrium distribution, establishing non-asymptotic estimates on mixing times, with explicit dependence on dimension and other relevant problem parameters. The results hold at a reasonable level of generality, and are often sharp in a suitable sense. The focus of the talk will be conceptual rather than technical, with an eye towards enabling intuition for i) which high-level aspects of the target distribution influence the convergence behaviour of RWM , and ii) which concrete properties must be verified in order to obtain a rigorous proof. A key element will be the impact of tail behaviour and measure concentration on the convergence profile of the algorithm across different time-scales.  No prior knowledge of the RWM is required from the audience. (joint work with C. Andrieu, A. Lee and A. Wang)

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

This talk is included in these lists:

• All CMS events
• Featured lists
• INI info aggregator
• Isaac Newton Institute Seminar Series
• School of Physical Sciences
• Seminar Room 1, Newton Institute
• bld31

Note that ex-directory lists are not shown.