Scholar
Ruben Seyer
Google Scholar ID: Oh_PuqIAAAAJ
PhD student in Mathematical Statistics, Chalmers/University of Gothenburg
Citations & Impact
Citations
14
H-index
2
i10-index
0
Publications
4
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Preprints: 1. 'Rebalancing Markov jump processes for non-reversible continuous-time sampling', 2025; 2. 'Gradient Estimation via Differentiable Metropolis-Hastings', 2024; Workshops: 'Differentiating Metropolis-Hastings to Optimize Intractable Densities', ICML 2023 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators; Theses: 'Differentiable Monte Carlo Samplers with Piecewise Deterministic Markov Processes', 2023.
Research Experience
- During his PhD, he focuses on designing non-reversible samplers and applying stochastic gradient methods to MCMC or piecewise deterministic Markov processes to automatically turn samplers into gradient samplers.
Education
- PhD: Mathematical Statistics, Chalmers University of Technology/University of Gothenburg, Supervisors: Moritz Schauer and Aila Särkkä; MScEng: Graduated from Chalmers University of Technology in 2023, Thesis: Differentiable Monte Carlo samplers using piecewise deterministic Markov processes.
Background
- Research Interests: Intersection of Bayesian inference and machine learning, particularly in Markov Monte Carlo methods and applications to spatial statistics and point processes. Professional Field: Mathematical Statistics.
Miscellany
- His personal website provides a substantial amount of notes which many students still find useful.
Co-authors