Tyler Farghly
Researcher and Musician
I am a PhD student at the University of Oxford supervised by Patrick Rebeschini and Arnaud Doucet in the OxCSML research group. I’m interested in theoretical foundations for machine learning and optimisation. Most recently, I have been interested in measures of generlisation, the use of noise for regularisation and the relationship between optimisation and sampling. Before my PhD, I studied Mathematics at Imperial College London, supervised by Grigorios A. Pavliotis.
I am also a musician, primarily focussed on Jazz drums. I regularly perform around Oxford and London and help to run a jam night in Oxford.
news
| Mar 9, 2023 | New preprint! Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality. |
|---|---|
| Dec 17, 2022 | I’m giving an oral presentation at CMStatistics 2022 for our new project adaptive Langevin Monte Carlo methods for heavy-tailed sampling via weighted functional inequalities. |
| Oct 10, 2022 | I’m co-organising a new reading group on topics addressing theoretical aspects of machine learning. These meetings are open to members of any department. |
| Jul 1, 2022 | I’m visiting the Vector Institute as a Research Intern over summer. I will be working with Professor Murat A. Erdogdu and his group on the theory of stochastic optimization and Langevin Monte Carlo. |