Théo Uscidda

According to our database, Théo Uscidda authored at least 7 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

On the potential of Optimal Transport in Geospatial Data Science.

Nina Wiedemann, Théo Uscidda, Martin Raubal

CoRR, 2024

Disentangled Representation Learning through Geometry Preservation with the Gromov-Monge Gap.

Théo Uscidda, Luca Eyring, Karsten Roth, Fabian J. Theis, Zeynep Akata, Marco Cuturi

CoRR, 2024

GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics.

Dominik Klein, Théo Uscidda, Fabian J. Theis, Marco Cuturi

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Mirror and Preconditioned Gradient Descent in Wasserstein Space.

Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, Anna Korba

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation.

Luca Eyring, Dominik Klein, Théo Uscidda, Giovanni Palla, Niki Kilbertus, Zeynep Akata, Fabian J. Theis

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Generative Entropic Neural Optimal Transport To Map Within and Across Spaces.

Dominik Klein, Théo Uscidda, Fabian J. Theis, Marco Cuturi

CoRR, 2023

The Monge Gap: A Regularizer to Learn All Transport Maps.

Théo Uscidda, Marco Cuturi

Proceedings of the International Conference on Machine Learning, 2023