USI - Email

Archive / INF Seminars / INF_2025_03_20_JunYang

USI - Email

	Stereographic Barker's MCMC Proposal: Efficiency and Robustness at Your Disposal

Host: Prof. Deborah Sulem, Prof. Igor Pivkin

Thursday

20.03

USI Campus EST, Room D5.01

12:30 - 13:30


	Jun Yang University of Copenhagen

Abstract: We introduce a new family of robust gradient-based MCMC samplers under the framework of stereographic MCMC (Yang et al. 2022) which maps the original high dimensional problem in Euclidean space onto a sphere. Compared with the existing Stereographic Projection Sampler (SPS) which is of a random-walk Metropolis type algorithm, our new family of samplers is gradient-based using the Barker proposal (Livingstone and Zanella, 2022), which improves SPS in high dimensions and is robust to tuning. Meanwhile, the proposed algorithms enjoy all the good properties of SPS, such as uniform ergodicity for a large class of heavy and light-tailed distributions and "blessings of dimensionality".

Joint work with Cameron Bell, Krzysztof Łatuszyński, Gareth O. Roberts, and Jeffrey S. Rosenthal.

Biography: Jun Yang joined Department of Mathematical Sciences, University of Copenhagen in 2023, as a (tenure-track) Assistant Professor of Statistics. From 2020 to 2023, he was a Florence Nightingale Bicentennial Fellow and Tutor in Computational Statistics and Machine Learning at Department of Statistics, University of Oxford. He got his Ph.D. in Statistics in 2020 from University of Toronto, advised by Daniel M. Roy and Jeffrey S. Rosenthal.