%0 Journal Article %T ICLR 2022 Challenge for Computational Geometry & Topology: Design and Results %+ University of California [Santa Barbara] (UC Santa Barbara) %+ University of California [Berkeley] (UC Berkeley) %+ University of Chicago %+ Atmo, USA %+ Ecole Polytechnique Fédérale de Lausanne (EPFL) %+ University of California [Los Angeles] (UCLA) %+ Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay) %+ E-Patient : Images, données & mOdèles pour la médeciNe numériquE (EPIONE) %+ PayAnalytics Iceland %+ Danmarks Tekniske Universitet = Technical University of Denmark (DTU) %+ University of Copenhagen = Københavns Universitet (UCPH) %+ Norwegian University of Science and Technology (NTNU) %+ Columbia University [New York] %+ Freie Universität Berlin %+ Zuse Institute Berlin (ZIB) %A Myers, Adele %A Utpala, Saiteja %A Talbar, Shubham %A Sanborn, Sophia %A Shewmake, Christian %A Donnat, Claire %A Mathe, Johan %A Lupo, Umberto %A Sonthalia, Rishi %A Cui, Xinyue %A Szwagier, Tom %A Pignet, Arthur %A Bergsson, Andri %A Hauberg, Soren %A Nielsen, Dmitriy %A Sommer, Stefan %A Klindt, David %A Hermansen, Erik %A Vaupel, Melvin %A Dunn, Benjamin %A Xiong, Jeffrey %A Aharony, Noga %A Pe'Er, Itsik %A Ambellan, Felix %A Hanik, Martin %A Nava-Yazdani, Esfandiar %A von Tycowicz, Christoph %A Miolane, Nina %< avec comité de lecture %@ 1938-7228 %J Proceedings of Machine Learning Research %I PMLR %S Topological, Algebraic and Geometric Learning Workshops 2022 %V 196 %P 269-276 %8 2022-11-09 %D 2022 %Z 2206.09048 %R 10.5281/zenodo.6554616 %Z Computer Science [cs]/Computational Geometry [cs.CG]Journal articles %X This paper presents the computational challenge on differential geometry and topology that was hosted within the ICLR 2022 workshop “Geometric and Topo- logical Representation Learning”. The competition asked participants to provide implementations of machine learning algorithms on manifolds that would respect the API of the open-source software Geomstats (manifold part) and Scikit-Learn (machine learning part) or PyTorch. The challenge attracted seven teams in its two month duration. This paper describes the design of the challenge and summarizes its main findings. %G English %2 https://hal.science/hal-03903044/document %2 https://hal.science/hal-03903044/file/myers22a%20%281%29.pdf %L hal-03903044 %U https://hal.science/hal-03903044 %~ INRIA %~ ENS-CACHAN %~ INRIA-SOPHIA %~ INRIASO %~ OPENAIRE %~ INRIA_TEST %~ TESTALAIN1 %~ INRIA2 %~ INRIA-EPFL %~ UNIV-COTEDAZUR %~ ENS-PARIS-SACLAY %~ INRIA-ETATSUNIS