Andi Q. Wang's Personal Page
Research interests
Monte Carlo methods
Bayesian inference
Quasi-stationarity
Scalable methods
Adaptive methods
Nonreversible processes
Address:
Andi Wang
Office 2.15
Department of Statistics
University of Warwick
Coventry
CV4 7AL
UK
Email:
firstname dot lastname @warwick.ac.uk
I am an Assistant Professor at the Department of Statistics at the University of Warwick.
My research is on the interface of computational statistics and applied probability, largely focussed on the theory and methodology of MCMC methods. Recently I have been particularly interested in subgeometric convergence and nonreversible methods.
This is my personal page, but see also my university page, and Google scholar.
Previously I was a post doctoral researcher (2019-2022) at the University of Bristol, working with Prof. Christophe Andrieu and Prof Anthony Lee and Dr. Sam Power, funded by CoSInES. I did my DPhil (PhD) at the Department of Statistics, University of Oxford, (2015-2019), on the OxWaSP CDT program, under the joint supervision of Prof. David Steinsaltz and Prof. Gareth Roberts. Prior to that I did my undergraduate and master's degree in Mathematics at the University of Cambridge (2011-2015).
Co-authors: Christophe Andrieu, Augustin Chevallier, Paul Dobson, Paul Fearnhead, Hector McKimm, Martin Kolb, Anthony Lee, Murray Pollock, Sam Power, Christian Robert, Gareth Roberts, Daniel Rudolf, Björn Sprungk, David Steinsaltz.
Publications
Journal articles and preprints
Power, S., Rudolf, D., Sprungk, B., Wang, A.Q., 2024. Weak Poincaré inequality comparisons for ideal and hybrid slice sampling, arXiv.
Chevallier, A., Power, S., Wang, A.Q., Fearnhead, P., 2024. PDMP Monte Carlo methods for piecewise-smooth densities, Advances in Applied Probability, DOI, arXiv.
Andrieu, C., Lee, A., Power, S., Wang, A.Q., 2023. Weak Poincaré Inequalities for Markov chains: theory and applications, arXiv.
Andrieu, C., Lee, A., Power, S., Wang, A.Q., 2024+. Explict convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles, to appear in The Annals of Applied Probability, arXiv.
McKimm, H, Wang, A.Q., Pollock, M, Robert, C.P., Roberts, G.O., 2024+. Sampling using adaptive regenerative processes, to appear in Bernoulli, arXiv.
Andrieu, C., Lee, A., Power, S., Wang, A.Q., 2022. Poincaré inequalities for Markov chains: a meeting with Cheeger, Lyapunov and Metropolis, technical report, arXiv.
Andrieu, C., Lee, A., Power, S., Wang, A.Q., 2022. Comparison of Markov chains via weak Poincaré inequalities with application to pseudo-marginal MCMC, The Annals of Statistics, 50(6): 3592-3618, DOI, arXiv.
Rudolf, D., Wang, A.Q., 2021. Perturbation theory for killed Markov processes and quasi-stationary distributions, arXiv.
Andrieu, C., Dobson, P., Wang, A.Q., 2021. Subgeometric hypocoercivity for piecewise-deterministic Markov process Monte Carlo methods, Electronic Journal of Probability, 26: 1-26 arXiv, DOI, video.
Wang, A.Q., Pollock, M, Roberts, G.O., Steinsaltz, D., 2021. Regeneration-enriched Markov processes with application to Monte Carlo, The Annals of Applied Probability, 31 (2): 703-735, DOI, short video.
Wang, A.Q., Roberts, G.O., Steinsaltz, D., 2020, An approximation scheme for quasi-stationary distributions of killed diffusions, Stochastic Processes and their Applications, 130 (5), 3193-3219, DOI.
Wang, A.Q., Kolb, M., Roberts, G.O., Steinsaltz, D., 2019, Theoretical properties of quasi-stationary Monte Carlo methods, The Annals of Applied Probability, 29 (1), 434-457, DOI.
Wang, A.Q., Steinsaltz, D., 2019. A note on the jump locations of Markov processes, arXiv.
Theses
Wang, A.Q., 2019. Theory of Killing and Regeneration in Continuous-time Monte Carlo Sampling. DPhil Thesis, University of Oxford, ORA.
Wang, A.Q., 2015. Nonparametric Inference Under Shape Constraints, 2015. Part III (Master's) essay, University of Cambridge, video.
Discussions
Wang, A.Q., 2023. Discussion of “the Discussion Meeting on Probabilistic and statistical aspects of machine learning”, on the paper "From Denoising Diffusions to Denoising Markov Models" by Benton, Shi, De Bortoli, Deliginanidis and Doucet, DOI.
Wang, A.Q, 2020. Discussion of "Quasi-stationary Monte Carlo and the ScaLE algorithm" by Pollock, Fearnhead, Johanson and Roberts, JRSS B 82 (5) 1212-1213, DOI. Additional discussions co-authored with:
Koskela, J. 1216-1217.
McKimm, H. 1213-1214.
Rudolf, D. 1214-1215.
Steinsaltz, D. 1214.
Wang, A.Q., Pollock, M, Roberts, G.O., Steinsaltz, D., 2020. Discussion of "Unbiased Markov chain Monte Carlo with couplings'' by Jacob, O'Leary and Atchade, JRSS B. Short video.
Other
Wang, A.Q., 2021. Microthesis: Quasi-stationary Monte Carlo methods, LMS Newsletter (492), link.
Notes
Notes on Transformers.
High-Dimensional Statistics reading group: notes on Chapter 4: Uniform Laws of Large Numbers.
Reinforcement learning reading group: notes on Deep Q-learning.
Neural networks reading group: notes on "Hopfield networks is all you need": jamboard.
Notes on Liu, Zhu, Belkin (2021): jamboard.
Warwick PDMP reading group: slides on convergence theory of PDMP MCMC methods.
High-dimensional stats reading groups: Notes on Implicit Regularization in Deep Learning; based on Bartlett et. al. (2021).