Join us for the fourth edition of the Virtual OTML Workshop @ NeurIPS!
Over the last few years, optimal transport (OT) has quickly become a central topic in machine learning. OT is now routinely used in many areas of ML, ranging from the theoretical use of OT flow for controlling learning algorithms to the inference of high-dimensional cell trajectories in genomics. The OTML workshop series (in ’14, ’17, ’19) has been instrumental in shaping this research thread. For this new installment of OTML, we aim even bigger by hosting an exceptional keynote speaker, Alessio Figalli, who received the 2018 Fields Medal for his breakthroughs in the analysis of the regularity properties of OT. OTML will be a unique opportunity for cross-fertilization between recent advances in pure mathematics and challenging high-dimensional learning problems.
The format of the workshop will encourage discussion and presentation of contributed content in addition to our lineup of invited talks.
Invited Speakers
Plenary Speakers
- Alessio Figalli (ETH Zurich)
- Caroline Uhler (MIT)
- Lénaïc Chizat (EPFL)
Keynote Talks
- Beatrice Acciaio (ETH Zurich)
- Chin-Wei Huang (MILA)
- Pinar Demetci (Brown)
- Yongxin Chen (Georgia Tech)
- Yunan Yang (Courant)
Awards
Best paper awards
- Discrete Schrödinger Bridges with Applications to Two-Sample Homogeneity Testing. Zaid Harchaoui, Lang Liu, Soumik Pal
- Entropic estimation of optimal transport maps. Aram-Alexandre Pooladian, Jonathan Niles-Weed
Runner up award
- Implicit Riemannian Concave Potential Maps. Danilo Jimenez Rezende, Sebastien Racaniere
Past Editions
Partners
