Peter Potaptchik

peter.potaptchik@stats.ox.ac.uk

peter_potaptchik@seas.harvard.edu

I’m a DPhil student in the Department of Statistics at the University of Oxford, advised by George Deligiannidis, Saifuddin Syed, and Yee Whye Teh. I’m currently based at Harvard University as a Visiting Fellow, working with Michael Albergo.

My research is supported by a Google PhD Fellowship, an NSERC Postgraduate Scholarship, and the EPSRC StatML CDT.

Previously, I worked with Chris J. Maddison and Daniel Roy at the University of Toronto, where I completed my BSc in Computer Science and Statistics.

Feel free to reach out if you’d like to collaborate or just chat!

News

Oct 17, 2024	Our preprint Linear Convergence of Diffusion Models Under the Manifold Hypothesis is out. In the context of ImageNet, our work suggests using ~100 steps (intrinsic dim) for effective sampling, compared to the existing state-of-the-art bounds, which recommend ~150k steps (ambient dim).
Sep 25, 2024	Our paper Metric Flow Matching for Smooth Interpolations on the Data Manifold was accepted at NeurIPS 2024.
Dec 26, 2023	Our preprint de Finetti’s theorem and the existence of regular conditional distributions and strong laws on exchangeable algebras is out on arxiv.
Nov 27, 2023	My talk at BAYSM (j-ISBA’s meeting) won the short talk award.
Sep 24, 2023	I started my DPhil at the University of Oxford!