Embedded Files
Hello! My name is Sam, and I am a researcher in Statistics.
I am currently Lecturer in Statistical Science at the University of Bristol.
Prior to this role, I was a Senior Research Associate (also at the University of Bristol) working with Prof. Christophe Andrieu on the Bayes4Health grant, and also collaborating closely with Prof. Anthony Lee.
Even further in the past, I was a PhD student at the University of Cambridge, working with Dr. Sergio Bacallado. You can find an online copy of my dissertation here.
News
With some friends, we have launched an online "International Seminar on Monte Carlo Methods", taking place weekly. We aim to bring in speakers across diverse fields, from mathematics, statistics, computer science, natural sciences, and more, to showcase the broad applicability and interest of these methods. See our website for further details.
Keywords
Computational Statistics
Monte Carlo Methods
Numerical Analysis
Bayesian Modelling
Research Interests
My research interests center around the design and analysis of stochastic algorithms, with applications mainly to statistics. I am particularly interested in Monte Carlo methods, such as Markov Chain Monte Carlo and Sequential Monte Carlo, and how the implementation of these methods can be made automatic, robust, and efficient.
Manuscripts
Z. Liu, S. Power, Y. Chen - A New Proof of Sub-Gaussian Norm Concentration Inequality - arXiv
R. Caprio, S. Power, A.Q. Wang - Analysis of Multiple-try Metropolis via Poincaré inequalities - arXiv
A. Chevallier, S. Power, M. Sutton - Towards practical PDMP sampling: Metropolis adjustments, locally adaptive step-sizes, and NUTS-based time lengths - arXiv
S.W. Ober, S. Power, T. Diethe, H.B. Moss - Big Batch Bayesian Active Learning by Considering Predictive Probabilities - Proceedings of NeurIPS workshop on Bayesian Decision-making and Uncertainty, arXiv
Z. Shen, J. Knoblauch, S. Power, C. Oates - Prediction-Centric Uncertainty Quantification via MMD - Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 258:649-657, 2025, [ arXiv ]
A. Dhir, S. Power, M. van der Wilk - Bivariate Causal Discovery using Bayesian Model Selection - Proceedings of 41st International Conference on Machine Learning, arXiv
R. Caprio, J. Kuntz, S. Power, A.M. Johansen - Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities - arXiv, slides, YouTube
S. Power, D. Rudolf, B. Sprungk, A.Q. Wang - Weak Poincaré inequality comparisons for ideal and hybrid slice sampling - arXiv, slides
C. Andrieu, A. Lee, S. Power, A.Q. Wang - Weak Poincaré Inequalities for Markov chains: theory and applications - arXiv, slides
J.N. Lim, J. Kuntz, S. Power, A.M. Johansen - Momentum Particle Maximum Likelihood - Proceedings of 41st International Conference on Machine Learning, [arXiv], slides, YouTube
S. Duffield, S. Power, L. Rimella - A State-Space Perspective on Modelling and Inference for Online Skill Rating - Journal of the Royal Statistical Society Series C: Applied Statistics, 2024, 00, 1–21, [arXiv], slides, YouTube
C. Andrieu, A. Lee, S. Power, A.Q. Wang - Explicit convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles - The Annals of Applied Probability, 34(4), 2024 [arXiv], slides, YouTube, YouTube
L. Riou-Durand, P. Sountsov, J. Vogrinc, C.C. Margossian, S. Power - Adaptive Tuning for Metropolis Adjusted Langevin Trajectories - Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:8102-8116, 2023, [arXiv]
C. Andrieu, A. Lee, S. Power, A.Q. Wang - Poincaré inequalities for Markov chains: a meeting with Cheeger, Lyapunov and Metropolis - Technical Report, arXiv, slides
F. Pagani, A. Chevallier, S. Power, S. Cotter, T. House - NuZZ: Numerical Zig-Zag Sampling for General Models - Statistics and Computing, [arXiv]
C. Andrieu, A. Lee, S. Power, A.Q. Wang - Comparison of Markov chains via weak Poincaré inequalities with application to pseudo−marginal MCMC - The Annals of Statistics, 50(6), 2022, [arXiv], slides
A. Chevallier, S. Power, A.Q. Wang, P. Fearnhead - PDMP Monte Carlo methods for piecewise-smooth densities - Advances in Applied Probability, [arXiv]
S. Power, J. Vorstrup Goldman - Accelerated Sampling on Discrete Spaces with Non−Reversible Markov Processes - arXiv, GitHub, YouTube, YouTube, slides
See also my Google Scholar profile.
Collaborators (in alphabetical order)
Christophe Andrieu, Rocco Caprio, Yongxin Chen, Augustin Chevallier, Simon Cotter, Tom Diethe, Sam Duffield, Paul Fearnhead, Jacob Vorstrup Goldman, Thomas House, Adam Johansen, Jeremias Knoblauch, Juan Kuntz, Anthony Lee, Jen Ning Lim, Zishun Liu, Charles Margossian, Henry Moss, Chris Oates, Sebastian Ober, Filippo Pagani, Lorenzo Rimella, Lionel Riou-Durand, Daniel Rudolf, Zheyang Shen, Pavel Sountsov, Bjoern Sprungk, Matthew Sutton, Jure Vogrinc, Andi Q. Wang
Slides
I have given research talks about several of the works listed above, and I am generally very happy to share the slides which I use in these talks. The links above point to GitHub repositories which contain a few decks of slides from talks corresponding to the work in question, each of which will have been designed with a specific audience in mind. Some slide decks correspond to multiple projects, and so are re-linked a couple of times.
Short Courses
In recent years, I have occasionally been given the opportunity to deliver some short courses on topics which I find particularly interesting. In particular, I can highlight
A three-hour course on the topic of "Contractivity Analysis of Markov Processes", delivered as part of the CoSInES-Bayes4Health Masterclass on Optimal Transport, held in April 2023 at the University of Warwick. A video recording of this course is available upon request (by e.g. email).
A two-hour course on "Geometric Functional Inequalities for Markov Chains", delivered as part of the semester-long programme on "Stochastic Systems for Anomalous Diffusion", held from July to December of 2024 at the Isaac Newton Institute in Cambridge. A video recording of this course is available at this link.
If you are interested in having me deliver short courses to your { research group, seminar, students, etc. }, then please reach out directly.
Notes
S. Power - Hamiltonian Monte Carlo with Finite Differences - Drive
S. Power - Markov Chain Monte Carlo without Metropolis-Hastings - Drive
Education and Positions
(2024-): Lecturer in Statistical Science University of Bristol
(2020-2023): Postdoctoral Research Associate University of Bristol
(2016-2020): PhD University of Cambridge
(2010-2014): MMath University of Oxford
Contact Information
Email: sam.power@bristol.ac.uk
Twitter: @sp_monte_carlo
Bluesky: @spmontecarlo.bsky.social
Office: 1.83, Fry Building
I am happy to be contacted about my work, or other research-related topics, and generally prefer to begin a dialogue over email. Historically, I have also been known to tweet fairly regularly about research. I am happy to be contacted there in a less formal capacity.
Some of my postings are about publicly-available reference materials, some of which I have catalogued here.
Page updated
Google Sites
Report abuse