skip to content
Home

Department of Applied Mathematics and Theoretical Physics

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

Provably Convergent Data-Driven Convex-Nonconvex Regularization
Z Shumaylov, J Budd, S Mukherjee, C-B Schönlieb
(2023)
(link to publication)
The Curse of Recursion: Training on Generated Data Makes Models Forget
I Shumailov, Z Shumaylov, Y Zhao, Y Gal, N Papernot, R Anderson
(2023)
(link to publication)
Quantum initial conditions for curved inflating universes
MI Letey, Z Shumaylov, FJ Agocs, WJ Handley, MP Hobson, AN Lasenby
(2022)
(doi: 10.48550/arxiv.2211.17248)
Primordial power spectra from k-inflation with curvature
Z Shumaylov, W Handley
– Physical Review D
(2022)
105,
123532
(doi: 10.1103/physrevd.105.123532)
Primordial power spectra from $k$-inflation with curvature
Z Shumaylov, W Handley
(2021)
(doi: 10.48550/arxiv.2112.07547)
Manipulating SGD with Data Ordering Attacks
I Shumailov, Z Shumaylov, D Kazhdan, Y Zhao, N Papernot, MA Erdogdu, R Anderson
– Advances in Neural Information Processing Systems
(2021)
22,
18021
(link to publication)
Manipulating SGD with Data Ordering Attacks
I Shumailov, Z Shumaylov, D Kazhdan, Y Zhao, N Papernot, MA Erdogdu, R Anderson
– ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021)
(2021)
34,
(link to publication)
Learned convex regularizers for inverse problems
S Mukherjee, S Dittmer, Z Shumaylov, S Lunz, O Öktem, C-B Schönlieb
(2020)
(link to publication)
  • <
  • 2 of 2

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