ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results
arXiv:2108.09810
Abstract
This paper presents the computational challenge on differential geometry and topology that happened within the ICLR 2021 workshop "Geometric and Topological Representation Learning". The competition asked participants to provide creative contributions to the fields of computational geometry and topology through the open-source repositories Geomstats and Giotto-TDA. The challenge attracted 16 teams in its two month duration. This paper describes the design of the challenge and summarizes its main findings.
References in corpus (11)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Fast Graph Representation Learning with PyTorch Geometric
- Manopt, a Matlab toolbox for optimization on manifolds
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- The Topology ToolKit
- Geomstats: A Python Package for Riemannian Geometry in Machine Learning
- A Topology Layer for Machine Learning
- Predicting Neural Network Accuracy from Weights
- Persistent Cohomology and Circular Coordinates
- Fuzzy c-Means Clustering for Persistence Diagrams
- An Empirical Bayes Approach to Shrinkage Estimation on the Manifold of Symmetric Positive-Definite Matrices