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

Adele  Myers; Sophia  Sanborn; Claire Donnat Donnat; Stefan Horst Sommer

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

Adele Myers, Sophia Sanborn, Claire Donnat Donnat, Stefan Horst Sommer

Image Analysis, Computational Modelling and Geometry

Research output: Contribution to conference › Paper › Research

14 Downloads (Pure)

Abstract

This paper presents the computational challenge on differential geometry and topology that was hosted within the ICLR 2022 workshop ``Geometric and Topological 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.

Original language	English
Publication date	2022
Number of pages	8
Publication status	Published - 2022
Event	ICLR 2022 Workshop on Geometrical and Topological Representation Learnings - ICLR 2022 - Virtual Duration: 29 Apr 2022 → 29 Apr 2022

Workshop

Workshop	ICLR 2022 Workshop on Geometrical and Topological Representation Learnings - ICLR 2022
City	Virtual
Period	29/04/2022 → 29/04/2022

Access to Document

ICLR 2022 CHALLENGE FORFinal published version, 109 KBLicence: CC BY

Cite this

@conference{30d308c6115f4d559c6956f1cfc5ee6b,

title = "ICLR 2022 Challenge for Computational Geometry & Topology: Design and Results",

abstract = "This paper presents the computational challenge on differential geometry and topology that was hosted within the ICLR 2022 workshop ``Geometric and Topological 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.",

author = "Adele Myers and Sophia Sanborn and Donnat, {Claire Donnat} and Sommer, {Stefan Horst}",

year = "2022",

language = "English",

note = "ICLR 2022 Workshop on Geometrical and Topological Representation Learnings - ICLR 2022<br/> ; Conference date: 29-04-2022 Through 29-04-2022",

}

TY - CONF

T1 - ICLR 2022 Challenge for Computational Geometry & Topology

T2 - ICLR 2022 Workshop on Geometrical and Topological Representation Learnings - ICLR 2022<br/>

AU - Myers, Adele

AU - Sanborn, Sophia

AU - Donnat, Claire Donnat

AU - Sommer, Stefan Horst

PY - 2022

Y1 - 2022

N2 - This paper presents the computational challenge on differential geometry and topology that was hosted within the ICLR 2022 workshop ``Geometric and Topological 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.

AB - This paper presents the computational challenge on differential geometry and topology that was hosted within the ICLR 2022 workshop ``Geometric and Topological 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.

M3 - Paper

Y2 - 29 April 2022 through 29 April 2022

ER -