Scholar
Samuel Power
Google Scholar ID: ePQTKrEAAAAJ
Lecturer of Statistical Science, University of Bristol
Citations & Impact
Citations
235
H-index
9
i10-index
9
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- B. Mlodozeniec, I. Reid, S. Power, D. Krueger, M. Erdogdu, R.E. Turner, R. Grosse - Distributional Training Data Attribution - NeurIPS 2025
- 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 - NeurIPS workshop on Bayesian Decision-making and Uncertainty
- Z. Shen, J. Knoblauch, S. Power, C. Oates - Prediction-Centric Uncertainty Quantification via MMD - The 26th International Conference on Artificial Intelligence and Statistics
- A. Dhir, S. Power, M. van der Wilk - Bivariate Causal Discovery using Bayesian Model Selection - 41st International Conference on Machine Learning
- R. Caprio, J. Kuntz, S. Power, A.M. Johansen - Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities - Journal of Machine Learning Research
- S. Power, D. Rudolf, B. Sprungk, A.Q. Wang - Weak Poincaré inequality comparisons for ideal and hybrid slice sampling - arXiv
- C. Andrieu, A. Lee, S. Power, A.Q. Wang - Weak Poincaré Inequalities for Markov chains: theory and applications - Annals of Applied Probability
Research Experience
- Currently a Lecturer in Statistical Science at the University of Bristol; previously a Senior Research Associate at the University of Bristol, working with Prof. Christophe Andrieu on the Bayes4Health grant, and collaborating closely with Prof. Anthony Lee.
Education
- PhD - University of Cambridge, Advisor: Sergio Bacallado
Background
- Research interests include the design and analysis of stochastic algorithms, particularly Monte Carlo methods (such as Markov Chain Monte Carlo and Sequential Monte Carlo), and how to make the implementation of these methods automatic, robust, and efficient. On the mathematical side, he is interested in stability of stochastic processes, concentration of measure, geometric functional inequalities, and related topics.
Miscellany
- Co-launched an online 'International Seminar on Monte Carlo Methods' with some friends, and plans to give in-person seminars at several universities in the coming months.
Co-authors