Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
Paper
•
2407.09468
•
Published
•
1
Papers - NEML - Non-Euclidean Machine Learning
See also: "A Riemannian Framework for Tensor Computing" https://inria.hal.science/inria-00070743/file/RR-5255.pdf
-
-
Barycentric Subspace Analysis on Manifolds
Paper • 1607.02833 • Published • 1 -
Poincaré Embeddings for Learning Hierarchical Representations
Paper • 1705.08039 • Published • 1 -
Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding
Paper • 1712.09005 • Published • 1 -
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
Paper • 1802.03426 • Published • 1 -
Geometry of Sample Spaces
Paper • 2010.08039 • Published • 1 -
O(n)-invariant Riemannian metrics on SPD matrices
Paper • 2109.05768 • Published • 1 -
A geometric framework for asymptotic inference of principal subspaces in PCA
Paper • 2209.02025 • Published • 1 -
Manifold Learning by Mixture Models of VAEs for Inverse Problems
Paper • 2303.15244 • Published • 1 -
Flagfolds
Paper • 2305.10583 • Published • 1 -
Principal subbundles for dimension reduction
Paper • 2307.03128 • Published • 1 -
Poincaré ResNet
Paper • 2303.14027 • Published • 1 -
Riemannian Adaptive Optimization Methods
Paper • 1810.00760 • Published • 1 -
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Paper • 2305.19043 • Published • 1