talks

Adversarially-trained linear regression (November 2022)
Uppsala University, Sweden @ System and Control Division (Microseminar).

Related publications:

Surprises in adversarially-trained linear regression (2022). arXiv:2205.12695. Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön

Adversarial Attacks in Linear Regression (November 2022)
Seminars on Advances in Probabilistic Machine Learning @ Aalto University and ELLIS unit Helsinki.

Abstract: State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial attacks are a popular framework for studying these vulnerabilities. They consider worst-case input disturbances designed to maximize model error and got a lot of attention due to their impact on the performance of state-of-the-art models. Adversarial training considers extending model training with these examples and is an effective approach to defend against such attacks. This talk will explore adversarial attacks and training in linear regression. There is a strong reason for this focus, for linear regression, adversarial training can be formulated as a convex and quadratic problem. Moreover, many interesting phenomena that can be observed in nonlinear models are still present. The setup is used to study the role of high dimensionality in robustness. And to reveal the connection between adversarial training, parameter-shrinking methods and minimum-norm solutions.

Related publications:

Surprises in adversarially-trained linear regression (2022). arXiv:2205.12695. Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön

Learning signals and systems and its applications to electrocardiography (June 2022)
Aalto University, Finland @ Jobtalk (Online).

Related publications:

Automatic diagnosis of the 12-lead ECG using a deep neural network (2020). Nature Communications. Antônio H. Ribeiro, Manoel Horta Ribeiro, Gabriela M. M. Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton P. S. Ferreira, Carl R. Andersson, Peter W. Macfarlane, Wagner Meira Jr., Thomas B. Schön, Antonio Luiz P. Ribeiro

Overparameterized Linear Regression under Adversarial Attacks (June 2022)
University of British Columbia, Canada @ Christos Thrampoulidis group (Online).

Abstract: State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial attacks are a popular framework for studying these vulnerabilities and got a lot of attention due to their high impact on deep neural network performance. Adversarial training is one of the most effective approaches to defending against such adversarial examples and considers adversarially perturbed samples during training to produce more robust models. This talk will explore adversarial attacks and training in a simpler setting than it is usually studied, linear regression. There is a strong reason for this focus, for linear regression models adversarial training can be simplified into a convex and quadratic form. Moreover, a lot of interesting phenomena that can still be observed in nonlinear models are still present. The setup is used to study how high-dimensionality can be either a source of additional robustness or brittleness. And also to show, in the linear setting, similarities (and differences) between $\ell_\infty$-adversarial training and the lasso and between $\ell_2$-adversarial training and ridge regression.

Related publications:

Surprises in adversarially-trained linear regression (2022). arXiv:2205.12695. Antônio H. Ribeiro, Dave Zachariah, Thomas B. Schön

Deep Neural Networks for Automatic ECG Analysis (March 2022)
University of Luxembourg @ Systems Control Group, LCSB (Online).

Related publications:

Automatic diagnosis of the 12-lead ECG using a deep neural network (2020). Nature Communications. Antônio H. Ribeiro, Manoel Horta Ribeiro, Gabriela M. M. Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton P. S. Ferreira, Carl R. Andersson, Peter W. Macfarlane, Wagner Meira Jr., Thomas B. Schön, Antonio Luiz P. Ribeiro
Deep neural network estimated electrocardiographic-age as a mortality predictor (2021). Nature Communications. Emilly M. Lima, Antônio H. Ribeiro, Gabriela MM Paixão, Manoel Horta Ribeiro, Marcelo M. Pinto Filho, Paulo R. Gomes, Derick M. Oliveira, Ester C. Sabino, Bruce B. Duncan, Luana Giatti, Sandhi M. Barreto, Wagner Meira, Thomas B. Schön, Antonio Luiz P. Ribeiro
Atrial fibrillation risk prediction from the 12-lead ECG using digital biomarkers and deep representation learning (2021). European Heart Journal - Digital Health. Shany Biton, Sheina Gendelman, Antônio H Ribeiro, Gabriela Miana, Carla Moreira, Antonio Luiz P Ribeiro, Joachim A Behar

On the robustness of overparametrized models (Nov. 2021)
Uppsala University, Sweden @ System and Control Division (Microseminar).

Related publications:

Overparametrized Regression Under L2 Adversarial Attacks (2021). Workshop on the Theory of Overparameterized Machine Learning (TOPML). Antonio H Ribeiro, Thomas B Schön
Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics (2021). Proceedings of the 19th IFAC Symposium on System Identification (SYSID) - IFAC-PapersOnLine. Antônio H. Ribeiro, Johannes N. Hendriks, Adrian G. Wills, Thomas B. Schön

Aprendendo modelos para sinais e sistemas (Oct. 2021)
Premio UFMG de Teses.