no code implementations • ICLR 2021 • Matthew Willetts, Alexander Camuto, Tom Rainforth, Stephen Roberts, Chris Holmes
We make significant advances in addressing this issue by introducing methods for producing adversarially robust VAEs.
no code implementations • 25 Sep 2019 • Matthew Willetts, Alexander Camuto, Stephen Roberts, Chris Holmes
We develop a new method for regularising neural networks.
no code implementations • 25 Sep 2019 • Matthew Willetts, Alexander Camuto, Stephen Roberts, Chris Holmes
This paper is concerned with the robustness of VAEs to adversarial attacks.
no code implementations • 18 Feb 2020 • Alexander Camuto, Matthew Willetts, Brooks Paige, Chris Holmes, Stephen Roberts
Separating high-dimensional data like images into independent latent factors, i. e independent component analysis (ICA), remains an open research problem.
no code implementations • NeurIPS 2020 • Alexander Camuto, Matthew Willetts, Umut Şimşekli, Stephen Roberts, Chris Holmes
We study the regularisation induced in neural networks by Gaussian noise injections (GNIs).
no code implementations • 14 Jul 2020 • Alexander Camuto, Matthew Willetts, Stephen Roberts, Chris Holmes, Tom Rainforth
We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations.
1 code implementation • 13 Feb 2021 • Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris Holmes, Mert Gürbüzbalaban, Umut Şimşekli
In this paper we focus on the so-called `implicit effect' of GNIs, which is the effect of the injected noise on the dynamics of SGD.
no code implementations • 15 Feb 2021 • Ben Barrett, Alexander Camuto, Matthew Willetts, Tom Rainforth
We introduce an approach for training Variational Autoencoders (VAEs) that are certifiably robust to adversarial attack.
no code implementations • 31 May 2021 • Alexander Camuto, Matthew Willetts
We further demonstrate that adding Gaussian noise to the input of a VAE allows us to more finely control the frequency content and the Lipschitz constant of the VAE encoder networks.
no code implementations • NeurIPS 2021 • Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Şimşekli, Lingjiong Zhu
As our main contribution, we prove that the generalization error of a stochastic optimization algorithm can be bounded based on the `complexity' of the fractal structure that underlies its invariant measure.
no code implementations • 5 Feb 2024 • Tobin South, Alexander Camuto, Shrey Jain, Shayla Nguyen, Robert Mahari, Christian Paquin, Jason Morton, Alex 'Sandy' Pentland
In a world of increasing closed-source commercial machine learning models, model evaluations from developers must be taken at face value.