Geometric Machine Learning
PulseAugur coverage of Geometric Machine Learning — every cluster mentioning Geometric Machine Learning across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New AI method speeds up geometric machine learning computations
Researchers have developed a new method using conditional invertible neural networks, termed "flow charts," to approximate normal coordinates on Riemannian manifolds. This approach significantly speeds up the computatio…
-
Transformers learn symmetries in geometric machine learning, study finds
A new research paper explores how Transformer architectures learn to represent symmetries in geometric machine learning tasks, specifically focusing on point cloud datasets. The study identifies an order of learnability…
-
New algorithm enables efficient learning with group invariances
Researchers have developed a new polynomial-time algorithm for learning with exact group invariances, applicable to both finite and infinite groups. This advancement provides a computational explanation for the success …
-
New sparse data augmentation method offers provable optimization guarantees
Researchers have developed a new method for sparse data augmentation in nonconvex optimization problems, particularly relevant for geometric machine learning. This technique allows for the approximation of full data aug…
-
Geometric ML uses data curvature for unsupervised boundary detection
Researchers have introduced a new geometric framework called Mean Curvature Boundary Points (MCBP) for unsupervised learning, which focuses on the intrinsic curvature of data manifolds rather than traditional density-ba…