skip to content
Home

Faculty of Mathematics

 

Zakhar Shumaylov

I am a PhD student under supervision of Professor Carola Schönlieb at the Cambridge Image Analysis Group within DAMTP. I am also a member of the Cantab Capital Institute for the Mathematics of Information and the Maths4DL programme.

I am generally interested in applied mathematics, specifically problems arising at the intersection of optimization, deep learning, geometry, and inverse problems.

Publications

Mathematics in the age of artificial intelligence: A primer on key topics in the mathematical sciences that underpin AI
D Leslie, M Anjos, O Anosova, R Bearon, M Calder, J Carrillo, A Champneys, T Coates, S Cohen, J Enright, A Etheridge, D Higham, S Jaggi, V Kurlin, R Leese, V Maguire Rajpaul, C Marr, C Nemeth, D Nicolau, C Offen, L Pareschi, M Pereyra, Y Roudi, C-B Schönlieb, Z Shumaylov et al.
(2026)
(doi: 10.5281/zenodo.20538963)
Muon is Not That Special: Random or Inverted Spectra Work Just as Well
Z Shumaylov, ND Costa, P Zaika, B Mucsányi, A Massucco, Y Gelberg, C-B Schönlieb, Y Gal, P Hennig
(2026)
(link to publication)
Learning regularization functionals for inverse problems: a comparative study
J Hertrich, HS Wong, A Denker, S Ducotterd, Z Fang, M Haltmeier, Ž Kereta, E Kobler, O Leong, MS Salehi, C-B Schönlieb, J Schwab, Z Shumaylov, J Sulam, GS Wache, M Zach, Y Zhang, MJ Ehrhardt, S Neumayer
– Handbook of Numerical Analysis
(2026)
(doi: 10.1016/bs.hna.2026.04.001)
When is a System Discoverable from Data? Discovery Requires Chaos
Z Shumaylov, P Zaika, P Scholl, G Kutyniok, L Horesh, C-B Schönlieb
(2025)
(link to publication)
On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization
Z Shumaylov, V Tsiaras, Y Stylianou
(2025)
(link to publication)
Data-driven approaches to inverse problems
C-B Schönlieb, Z Shumaylov
(2025)
(link to publication)
AI models collapse when trained on recursively generated data (March , 10.1038/s41586-025-08905-3, 2025)
I Shumailov, Z Shumaylov, Y Zhao, N Papernot, R Anderson, Y Gal
– Nature
(2025)
640,
E6
(doi: 10.1038/s41586-025-08905-3)
LIE ALGEBRA CANONICALIZATION: EQUIVARIANT NEURAL OPERATORS UNDER ARBITRARY LIE GROUPS
Z Shumaylov, P Zaika, J Rowbottom, F Sherry, M Weber, CB Schönlieb
– 13th International Conference on Learning Representations Iclr 2025
(2025)
13401
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
W Diepeveen, G Batzolis, Z Shumaylov, CB Schönlieb
– Proceedings of Machine Learning Research
(2025)
267,
13746
Symplectic Neural Flows for Modeling and Discovery
P Canizares, D Murari, C-B Schönlieb, F Sherry, Z Shumaylov
(2024)
(link to publication)
  • 1 of 3
  • >

Research Group

Mathematics of Information (Applied)

Email

zs334@cam.ac.uk

Room

F0.01

Personal homepage

https://zakobian.github.io/

Study at Cambridge

About the University

Research at Cambridge