Search Results for author: Alexander Camuto

Found 11 papers, 1 papers with code

Verifiable evaluations of machine learning models using zkSNARKs

no code implementations5 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.

Fairness

Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms

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.

Generalization Bounds Learning Theory +1

Variational Autoencoders: A Harmonic Perspective

no code implementations31 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.

Adversarial Robustness

Certifiably Robust Variational Autoencoders

no code implementations15 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.

Adversarial Attack

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections

1 code implementation13 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.

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders

no code implementations14 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.

Learning Bijective Feature Maps for Linear ICA

no code implementations18 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.

Improving VAEs' Robustness to Adversarial Attack

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.

Adversarial Attack

Cannot find the paper you are looking for? You can Submit a new open access paper.