158 citations · 165 across the 2 of their papers we have counts for
5 papers
The Curse of Recursion: Training on Generated Data Makes Models Forget
Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao +3
Stable Diffusion revolutionised image creation from descriptive text. GPT-2, GPT-3(.5) and GPT-4 demonstrated astonishing performance across a variety of language tasks. ChatGPT in…
Quantum initial conditions for curved inflating universes
Mary I. Letey, Zakhar Shumaylov, Fruzsina J. Agocs +3
We discuss the challenges of motivating, constructing, and quantizing a canonically normalized inflationary perturbation in spatially curved universes. We show that this has histor…
Primordial power spectra from -inflation with curvature
Zakhar Shumaylov, Will Handley
We investigate the primordial power spectra for general kinetic inflation models that support a period of kinetic dominance in the case of curved universes. We present derivations…
Manipulating SGD with Data Ordering Attacks
Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan +4
Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained…
Learned convex regularizers for inverse problems
Subhadip Mukherjee, Sören Dittmer, Zakhar Shumaylov +3
We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional.…