ICLR 2022 Challenge for Computational Geometry & Topology: Design and Results

Adele Myers, Saiteja Utpala, Shubham Talbar, Sophia Sanborn, Christian Shewmake, Claire Donnat, Johan Mathe, Rishi Sonthalia, Xinyue Cui, Tom Szwagier, Arthur Pignet, Andri Bergsson, Søren Hauberg, Dmitriy Nielsen, Stefan Sommer, David Klindt, Erik Hermansen, Melvin Vaupel, Benjamin Dunn, Jeffrey Xiong, Noga Aharony, Itsik Pe’er, Felix Ambellan, Martin Hanik, Esfandiar Nava-Yazdani, Christoph von Tycowicz, Nina Miolane
Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, PMLR 196:269-276, 2022.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v196-myers22a, title = {ICLR 2022 Challenge for Computational Geometry & Topology: Design and Results}, author = {Myers, Adele and Utpala, Saiteja and Talbar, Shubham and Sanborn, Sophia and Shewmake, Christian and Donnat, Claire and Mathe, Johan and Sonthalia, Rishi and Cui, Xinyue and Szwagier, Tom and Pignet, Arthur and Bergsson, Andri and Hauberg, S\oren and Nielsen, Dmitriy and Sommer, Stefan and Klindt, David and Hermansen, Erik and Vaupel, Melvin and Dunn, Benjamin and Xiong, Jeffrey and Aharony, Noga and Pe'er, Itsik and Ambellan, Felix and Hanik, Martin and Nava-Yazdani, Esfandiar and Tycowicz, Christoph von and Miolane, Nina}, booktitle = {Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022}, pages = {269--276}, year = {2022}, editor = {Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Kaul, Manohar and Ktena, Ira and Kvinge, Henry and Miolane, Nina and Rieck, Bastian and Tymochko, Sarah and Wolf, Guy}, volume = {196}, series = {Proceedings of Machine Learning Research}, month = {25 Feb--22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v196/myers22a/myers22a.pdf}, url = {https://proceedings.mlr.press/v196/myers22a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T ICLR 2022 Challenge for Computational Geometry & Topology: Design and Results %A Adele Myers %A Saiteja Utpala %A Shubham Talbar %A Sophia Sanborn %A Christian Shewmake %A Claire Donnat %A Johan Mathe %A Rishi Sonthalia %A Xinyue Cui %A Tom Szwagier %A Arthur Pignet %A Andri Bergsson %A Søren Hauberg %A Dmitriy Nielsen %A Stefan Sommer %A David Klindt %A Erik Hermansen %A Melvin Vaupel %A Benjamin Dunn %A Jeffrey Xiong %A Noga Aharony %A Itsik Pe’er %A Felix Ambellan %A Martin Hanik %A Esfandiar Nava-Yazdani %A Christoph von Tycowicz %A Nina Miolane %B Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022 %C Proceedings of Machine Learning Research %D 2022 %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Manohar Kaul %E Ira Ktena %E Henry Kvinge %E Nina Miolane %E Bastian Rieck %E Sarah Tymochko %E Guy Wolf %F pmlr-v196-myers22a %I PMLR %P 269--276 %U https://proceedings.mlr.press/v196/myers22a.html %V 196 %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.
APA
Myers, A., Utpala, S., Talbar, S., Sanborn, S., Shewmake, C., Donnat, C., Mathe, J., Sonthalia, R., Cui, X., Szwagier, T., Pignet, A., Bergsson, A., Hauberg, S., Nielsen, D., Sommer, S., Klindt, D., Hermansen, E., Vaupel, M., Dunn, B., Xiong, J., Aharony, N., Pe’er, I., Ambellan, F., Hanik, M., Nava-Yazdani, E., Tycowicz, C.v. & Miolane, N.. (2022). ICLR 2022 Challenge for Computational Geometry & Topology: Design and Results. Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, in Proceedings of Machine Learning Research 196:269-276 Available from https://proceedings.mlr.press/v196/myers22a.html.

Related Material