Guillermo Ortiz-Jiménez

PhD Student

École Polytechnique Fédérale de Lausanne (EPFL)

Hi! I’m Guille

I’m a PhD student at EPFL working under the supervision of Prof. Pascal Frossard. My current research focuses on understanding deep learning by studying the complex interactions between datasets, architectures and optimization. In my work, I am providing a novel framework to design better and more reliable neural networks that exploit prior knowledge about the world.

Before starting my PhD, I lived in The Netherlands for two years, where I worked on sampling theory for tensors and network data at TU Delft. In the past, I have also spent some great time in Germany at Philips Research in Hamburg doing research on self-supervised deep learning for medical imaging. Not so long ago, I was an undergraduate student at Universidad Politecnica de Madrid, Spain.

Interests

Deep learning
Robustness
Generalization

Education

PhD in Machine Learning, Ongoing

École Polytechnique Fédérale de Lausanne
MSc in Electrical Engineering, 2018

Delft University of Technology
BSc in Telecommunications Eng., 2015

Universidad Politécnica de Madrid

Featured publications

G. Ortiz-Jimenez, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard

December 2020 NeurIPS 2020

Neural Anisotropy Directions

We analyze the role of the network architecture in shaping the inductive bias of deep classifiers. Specifically, we introduce the neural anisotropy directions (NADs) of a network as the vectors that encapsulate the directional inductive bias of an architecture. These vectors, encode the preference of a network to separate the input data based on some particular features.

PDF Blog Code Video

G. Ortiz-Jimenez, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard

December 2020 NeurIPS 2020

Hold me tight! Influence of discriminative features on deep network boundaries

Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates dataset features to the distance of samples to the decision boundary. Specifically, we rigorously confirm that neural networks exhibit a high invariance to non-discriminative features, and show that very small perturbations of the training samples in certain directions can lead to sudden invariances in the orthogonal ones.

PDF Code

Research trajectory

PhD Researcher

EPFL

Nov 2018 – Present Lausanne, Switzerland

Studying the inductive bias of deep learning and how it affects its generalization and robustness properties. My research has already provided insights to improve adversarial defenses, out-of-distribution generalization, and to understand the role of architecture in deep learning.

Research Intern

Philips Healthcare Research

Jul 2017 – Oct 2017 Hamburg, Germany

As a research intern, I was involved in different projects related to computational medical imaging and fetal ultrasound. In particular, I was in charge of the development of different self-supervised deep learning algorithms for representation learning and medical image reconstruction.

Master Student

Delft University of Technology

Sep 2016 – Aug 2018 Delft, Netherlands

For my master thesis I carried out research on deep learning for multidomain graphs and on sparse sampling for inverse problems with tensors.

Research Assistant

Microwaves and Radar Group, UPM

Jul 2015 – Jul 2016 Madrid, Spain

During my time at the group, I developed a complete electromagnetic simulator for the mm-wave radar that the group was developing for airport security applications. In particular, we were one of the first groups to propose the use of 3D rendering techniques from computer graphics to accurately model the scattering from the human skin at the submillimeter band.

Best ICT Graduate

Universidad Politécnica de Madrid Jan 2016

Best student among all students graduating at UPM in a degree related to Information and Communications Technology (ICT).

Valedictorian

Faculty of Telecommunications. Universidad Politécnica de Madrid Jan 2016

Top student of the Faculty of Telecommunications.

Academic Excellence Scholarship

Autonomous Community of Madrid Sep 2012 – Aug 2015

Yearly allowance to the top undergraduate students in Madrid.

Publications

Ordered by date

Check my Google Scholar for an updated list or quickly discover relevant content by filtering publications.

G. Ortiz-Jimenez, S.M. Moosavi-Dezfooli, P. Frossard (2021). What can linearized neural networks actually say about generalization?. NeurIPS 2021.

G. Ortiz-Jimenez, I.F. Salazar-Reque, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard (2021). A neural anisotropic view of underspecification in deep learning. RobustML Workshop (ICLR 2021).

G. Ortiz-Jimenez, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard (2020). Neural Anisotropy Directions. NeurIPS 2020.

G. Ortiz-Jimenez, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard (2020). Hold me tight! Influence of discriminative features on deep network boundaries. NeurIPS 2020.

G. Ortiz-Jimenez, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard (2020). Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness. Proceedings of IEEE.

G. Ortiz-Jimenez, A. Modas, S.M. Moosavi-Dezfooli, P. Frossard (2020). Redundant features can hurt robustness to distribution shift. UDL Workshop (ICML 2020).

C. Vignac, G. Ortiz-Jimenez, P. Frossard (2020). On the Choice of Graph Neural Network Architectures. IEEE ICASSP 2020.

G. Ortiz-Jimenez, M. El Gheche, E. Simou, H.P. Maretic, P. Frossard (2020). Forward-Backward Splitting for Optimal Transport based Problems. IEEE ICASSP 2020.

G. Ortiz-Jimenez, M. El Gheche, E. Simou, H.P. Maretic, P. Frossard (2019). CDOT: Continuous Domain Adaptation using Optimal Transport. OTML Workshop (NeurIPS 2019).

G. Ortiz-Jimenez, M. Coutino, S. Chepuri, G. Leus (2019). Sparse Sampling For Inverse Problems with Tensors. IEEE Transactions of Signal Processing.

G. Ortiz-Jimenez, M. Coutino, S. Chepuri, G. Leus (2018). Sampling and Reconstruction of Signals on Product Graphs. IEEE GlobalSIP 2018.

G. Ortiz-Jimenez (2018). Multidomain Graph Signal Processing. MSc Thesis.

G. Ortiz-Jimenez, F. Garcia-Rial, L. A. Ubeda-Medina, R. Pages, N. Garcia, J. Grajal (2017). Simulation Framework for a 3-D High-Resolution Imaging Radar at 300 GHz with a Scattering Model Based on Rendering Techniques. IEEE Transactions on Terahertz Science and Technology.