I'm Valentina, a doctoral researcher in Machine Learning. For the past year, I have been carrying out research as an independent researcher while waiting for the work authorization (O1 visa) to move to the US and join GE Global Research. Unfortunately, recent presidential proclamations for facing COVID are slowing down even further this process.
My research interests cover metric learning, weakly-labeled data, local learning and decentralized learning, adversarial robustness and ML applied to climate science.
I received my PhD in Computer Science from Jean Monnet University (Saint-Etienne, France), in the Data Intelligence team of Hubert Curien Lab., supervised by Marc Sebban and Rémi Emonet. My PhD focused on kernel learning with theoretical guarantees on performance. In particular, studying new data-dependent ways for approximating the Gram matrix and for learning the kernel function as well, through the selection of representing inputs.
In 2020 and 2019, I took part in FDL research accelerator, working on Deep Learning applied to climate science, in particular for performing cloud classification and weather forecasting at global scale and from satellite imagery. An outcome of these projects was the release of CUMULO dataset.
In 2017, I worked as an intern at IBM Research, Dublin, in Mathieu Sinn's team, on studying and building Deep Learning architectures robust to adversarial examples. The library developped for this research work served as codebase of the initial release of Adversarial Robustness Toolbox.
Previously, I graduated in 2015 from INSA de Lyon, France, in Computer Science.