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.
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 • 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 • 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.
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 • 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.
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 • 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 • 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.