Tyler Farghly
computation · mathematics · music

PhD student @ Oxford Statistics; working on theoretical foundations of machine learning. Supervised by Patrick Rebeschini and Arnaud Doucet in the OxCSML research group. Currently interested in diffusion models, stochastic optimisation and algorithm-dependent theories of generalisation.
Also a musician, primarily focussed on Jazz drums. Regularly perform around Oxford and London. Occasionally produce electronic music.
news
Sep 2025 | Visiting University of Copenhagen Mathematics. Giving a talk on Sept 4th |
---|---|
Jul 2025 | â« Showing a soundscape as part of a collaborative exhibition, âThis Place is a Messageâ at Mezzanine Studios |
Jul 2025 | â New preprint! Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis |
May 2025 | â Article featured in Journal for the Philosophy of Planetary Computation: Cognitive Infrastructures: Conjectural Explorations of AI as a Physical Actor in the Wild |
May 2025 | â« Released an album with the Small Claims Trio: Listen to âSmall Claimsâ |
Mar 2025 | Presenting our work at ALT 2025 in Milan: Generalisation under gradient descent via deterministic PAC-Bayes |
Jun 2024 | Working at Antikytheraâs Cognitive Infrastructures Studio as a Studio Researcher over the summer |
Apr 2024 | â Article featured in JMLR: Mean-Square Analysis of Discretized ItĂŽ Diffusions for Heavy-tailed Sampling |
selected papers
- Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry AdaptiveDraft available on request 2025