"Basically, I’m not interested in doing research and I never have been. I’m interested in understanding, which is quite a different thing. And often to understand something you have to work it out yourself because no one else has done it"
"Getting numbers is easy; getting numbers you can trust is hard."
This very infrequent blog is by me, Nicola Branchini.
I am a graduate researcher in Statistics in the School of Mathematics at the University of Edinburgh, advised by Prof. Víctor Elvira.
I am interested broadly in statistical methodology around efficient uncertainty quantification, decision making, probabilistic reasoning, computational statistics, and machine learning.
More specifically, I am interested in methods for (possibly adaptive) Importance Sampling, experimental design, and causal inference.
I like collaborating with people. If you do research in very related topics, feel free to drop me an email.
Some specific topics I am working on now directly and/or want to use in my work in the future are:
- (Adaptive/annealed) importance sampling and quasi Monte Carlo methodology for joint estimation of multiple related quantities.
- Measure transport and optimal transport methodology
- Applications in rare event estimation.
- Applications in causal inference, in particular methods to combine interventional and observational data to make sample-efficient inferences in causal models.
Statistics and Probability Letters
AISTATS 2023, AABI (workshop) 2023, NeurIPS 2023
Talks & Posters
- Contributed talk on “Generalized Self Normalized Importance Sampling” at the 14th international conference on Monte Carlo methods and applications (MCM) 2023
- Poster on “Generalized Self Normalized Importance Sampling” at BayesComp 2023.
- Poster on “Causal Entropy Optimisation” at Greek Stochastics.
- Poster: Optimized Auxiliary Particle Filters: adapting mixture proposals via convex optimization, at 5th Workshop on Sequential Monte Carlo methods, May 2022.
- Poster: Optimized Auxiliary Particle Filters: adapting mixture proposals via convex optimization, at “Bayes at CIRM” Winter School, Centre International de Rencontres Mathématiques, Marseille, October 2021
- Poster: Optimized Auxiliary Particle Filters: adapting mixture proposals via convex optimization at 37th Conference on Uncertainty in Artificial Intelligence (UAI), online, 2021.
Previously, I was a Research Assistant at the Alan Turing Institute, working within the Warwick Machine Learning Group and supervised by Prof. Theo Damoulas. Previous to that, I was a Master’s student in the School of Informatics at the University of Edinburgh where I was supervised by Dr. Víctor Elvira working on auxiliary particle filters.
As undergrad, I studied Computer Science at the University of Warwick, where I did my BSc dissertation on reproducing AlphaZero supervised by Dr. Paolo Turrini.
Random selection of nice reads
Worth having the physical version.
- Noise: A Flaw in Human Judgment, Daniel Kahneman, Olivier Sibony, Cass R. Sunstein
- The book of why, Judea Pearl & Dana McKenzie
- The Meaning of It All: Thoughts of a Citizen Scientist, Richard Feynman.
- Sustainable energy - without the hot air, David McKay
- The Art of Statistics: Learning from Data, David Spiegelhalter
- Knock on Wood: Luck, Chance, and the Meaning of Everything, Jeffrey S. Rosenthal