Metropolis Adjusted Langevin Trajectories: a robust alternative to Hamiltonian Monte Carlo

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

• Lionel Riou-Durand (University of Warwick)
• Wednesday 11 May 2022, 14:00-15:00
• Centre for Mathematical Sciences, MR14.

If you have a question about this talk, please contact Randolf Altmeyer.

Hamiltonian Monte Carlo (HMC) is a widely used sampler, known for its efficiency on high dimensional distributions. Yet HMC remains quite sensitive to the choice of integration time. Randomizing the length of Hamiltonian trajectories (RHMC) has been suggested to smooth the Auto-Correlation Functions (ACF), ensuring robustness of tuning. We present the Langevin diffusion as an alternative to control these ACFs by inducing randomness in Hamiltonian trajectories through a continuous refreshment of the velocities. We connect and compare the two processes in terms of quantitative mixing rates for the 2-Wasserstein and L2 distances. The Langevin diffusion is presented as a limit of RHMC achieving the fastest mixing rate for strongly log-concave targets. We introduce a robust alternative to HMC built upon these dynamics, named Metropolis Adjusted Langevin Trajectories (MALT). Studying the scaling limit of MALT , we obtain optimal tuning guidelines similar to HMC , and recover the same scaling with respect to the dimension without additional assumptions. We illustrate numerically the efficiency of MALT compared to HMC and RHMC .

This talk is part of the CCIMI Seminars series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CCIMI
• CCIMI Seminars
• CMS Events
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Centre for Mathematical Sciences, MR14
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Trust & Technology Initiative - interesting events
• bld31
• custom
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.