conftrace_

Théo Uscidda

5 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

ICLR (2) NeurIPS (2) ICML (1)

Top co-authors

Marco Cuturi (3) Zeynep Akata (2) Fabian J Theis (2) Luca Eyring (2) Dominik Klein (2) Pierre-Cyril Aubin-Frankowski (1) Clément Bonet (1) Niki Kilbertus (1) Karsten Roth (1) Anna Korba (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Deep Learning (2) Mathematics & Optimization (2) Models (2) Optimization (2) Application Areas (1) Core Methods (1) Mathematics (1)

Keywords

optimal transport (4) flow matching (1) continuous optimization (1) gradient descent (1) mirror descent (1) quadratic programming (1) disentangled representation (1) wasserstein space (1) domain translation (1) sinkhorn divergence (1) preconditioned gradient descent (1) unbalanced optimal transport (1) transport map (1) geometric feature (1) unpaired learning (1) input convex neural network (1) monge map (1) neural network (1) single-cell genomics (1) monge gap (1)

Papers

Disentangled Representation Learning with the Gromov-Monge Gap ICLR 2025 GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics NeurIPS 2024 Mirror and Preconditioned Gradient Descent in Wasserstein Space NeurIPS 2024 Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation ICLR 2024 The Monge Gap: A Regularizer to Learn All Transport Maps ICML 2023