Théo Uscidda
Ph.D. with Marco Cuturi @ CREST - ENSAE, Institut Polytechnique de Paris
Visiting Ph.D. hosted by Fabian Theis @ Helmholtz Munich, Technical University of Munich
Incoming Research Intern @ Flatiron Institute, Simons Foundation
Education: I am a Ph.D. student in machine learning working with Marco Cuturi (Apple MLR & CREST - ENSAE). Prior to that, I completed a master’s degree in mathematics, vision and learning at ENS Paris-Saclay, working with Claire Boyer (Sorbonne Université), Julie Josse (INRIA) and Boris Muzellec (Owkin). Moreover, I hold a bachelor’s degree form Télécom Paris, Institut Polytechnique de Paris.
Research: I work on the interplay between optimal transport (OT), generative modeling, and representational learning. Broadly speaking, I am committed to demonstrating how OT can be instrumental in various machine-learning contexts. Recently, I have developed a keen interest in applying OT to solve challenges arising in single-cell biology. Since February 2024, I have been visiting Fabian Theis at the Helmholtz, Technical University of Munich to further explore these ideas.
Apr 25, 2024 | I presented our paper on unbalanced Monge maps at the Google DeepMind’s reading group on generative models, transport and sampling, organized by Valentin de Bortoli. Looking forward to presenting it at ICLR 2024, in Vienna! |
---|---|
Jan 17, 2024 | Our paper on unbalanced Monge maps has been accepted to ICLR. See you in Vienna! |
Dec 1, 2023 | Starting from February 2024, I will visit Fabian Theis at Helmholtz, Technical University of Munich to work on generative modeling for single-cell biology. See you in Munich! |
Oct 18, 2023 | I am giving a long talk at IHES for the welcome day of the Université Paris-Saclay graduate school. |
Jul 25, 2023 | I am at ICML in Honolulu, Hawaii, presenting our paper The Monge Gap: A Regularizer to Learn All Transport Maps. See you at poster 333 togheter with Marco Cuturi! |