SEMINARS IN STATISTICS @ COLLEGIO CARLO ALBERTO https://www.carloalberto.org/events/category/seminars/seminars-in-statistics/page/2/?tribe-bar-date=2019-09-01
Venerdi 24 Maggio 2024, alle ore 12.00, presso il Collegio Carlo Alberto, in Piazza Arbarello 8, Torino, si terrà il seguente seminario:
------------------------------------------------ Speaker: Samuel Livingston (UCL UK)
Title: *Robust gradient-based sampling algorithms using skew-symmetric numerical schemes*
Abstract: State-of-the-art sampling algorithms for smooth continuous distributions are typically gradient-based, e.g. Langevin or Hamiltonian Monte Carlo. It is known, however, that particular features of the distribution to be sampled can cause them to be unstable/work poorly. The algorithms are typically based on a numerical simulation of some stochastic process (e.g. the overdamped Langevin diffusion), and the instability comes from the choice of numerical scheme. I will introduce a new explicit numerical scheme for diffusions, which has skew-symmetric increments, and can be used to design simple and fast sampling algorithms that are provably more robust. I will show that the resulting 'unadjusted Barker algorithm', so called because of its connection to the Barker Metropolis—Hastings algorithm of Livingstone & Zanella (JRSS B, 2022) is well-defined and converges at a geometric rate to an equilibrium which is close to the distribution of interest in many cases when the unadjusted Langevin algorithm is transient. ------------------------------------------------
Sarà possibile seguire il seminario anche in streaming: Join Zoom Meeting https://us02web.zoom.us/j/81530120491?pwd=YUV4Y2dtb1creEMvRkR5SkpmeW1sQT09
Il seminario è organizzato dalla "de Castro" Statistics Initiative
www.carloalberto.org/stats