Lucas Anquetil

Wasserstein learning of determinantal point processes

Determinantal point processes (DPPs) have received significant attention as an elegant probabilistic model for discrete subset selection. Most prior work on DPP learning focuses on maximum likelihood estimation (MLE). While efficient and scalable, MLE approaches do not leverage any subset similarity information and may fail to recover the true generative distribution of discrete data. In this work, by deriving a differentiable relaxation of a DPP sampling algorithm, we present a novel approach for learning DPPs that minimizes the Wasserstein distance between the model and data composed of observed subsets. Through an evaluation on a real-world dataset, we show that our Wasserstein learning approach provides significantly improved predictive performance on a generative task compared to DPPs trained using MLE.

Adversarial Dictionary Learning

This work frames the learning of multiple adversarial perturbations as a sparse dictionary learning problem bridging the gap between specific and universal attacks. On the one hand, this framework allows to build an adversary attack to new examples by only learning the coding vectors, provided that the dictionary is known. On the other hand, the a posteriori study of the atoms unveils the most common patterns to attack the classifier. Numerical experiments conducted on CIFAR-10 illustrate that our approach, termed as Sparse Coding of ADversarial Attacks (SCADA), achieves higher fooling rates of the deep model than state-of-the-art attacks for smaller adversarial perturbations.

PhD Student

I enrolled in the PhD program under the RAIMO project focused on the research toward safe Artificial Intelligence in mobility.

My PhD supervisor is M. Stéphane CANU and my PhD focus is the study of Neural Networks robustness

Research Intern

I worked in the Recommendation System team under the supervision of M. Mike GARTRELL.

We created a new way to train discrete generative models and published it at the NeurIPS 2020 LMCA workshop.

Study trip in India, Bangalore

I followed Computer Science and Data Science courses at the New Horizon College of Engineering in Bengaluru India, I discovered new ways of studying and completely different approach to life.

Research Intern

I assisted a PhD student on Conditional GAN, I was assigned the implementations of Conditional GANs and running the experiments on clusters.

PhD Student

I enrolled in the PhD program under the RAIMO project focused on the research toward safe Artificial Intelligence in mobility. My PhD supervisor is M. Stéphane CANU and my PhD focus is the study of Neural Networks robustness

Master of Science : Data Science

Through my Master's degree and the many university projects I lead, I gained expertise in Data Science and Mathematics. During my Master's projects I have been supervised by M. Alain Rakotomamonjy

Bachelor of Science : Computer Science

Completing a Bachelor's degree in Computer Science mainly has been very helpful, as I gained a strong background in Computer Science which allows me nowadays to work without any practical limitations.