Scholar
Tyler Farghly
Google Scholar ID: suXJdCIAAAAJ
University of Oxford
Citations & Impact
Citations
169
H-index
5
i10-index
4
Publications
10
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Papers: 'Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis' (preprint 2025), 'Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive' (draft 2025); Other Achievements: Article in Journal for the Philosophy of Planetary Computation 'Cognitive Infrastructures: Conjectural Explorations of AI as a Physical Actor in the Wild' (May 2025), article in JMLR 'Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling' (Apr 2024).
Research Experience
- Work Experience: Studio Researcher at Antikythera's Cognitive Infrastructures Studio; Research Projects: Working on diffusion models; Position: PhD student at Oxford Statistics.
Education
- Degree: PhD; University: Oxford; Supervisors: Patrick Rebeschini and Arnaud Doucet; Time: Current; Major: Statistics.
Background
- Research Interests: Diffusion models, stochastic optimisation, and algorithm-dependent theories of generalisation. Fields: Computation, mathematics, music. Bio: PhD student at Oxford Statistics, working on the theoretical foundations of machine learning.
Miscellany
- Interests: Jazz drummer, regularly performs around Oxford and London, occasionally produces electronic music.
Co-authors