URerF uses unsupervised decision forests on sparse linear feature combinations to estimate geodesic distances robustly under high-dimensional noise, outperforming Isomap, UMAP, and FLANN on simulated and connectome data.
A global geometric framework for nonlinear dimensionality reduction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Riemannian gradient descent on rank-r Gram matrices for EDMC achieves linear convergence with high probability for sampling probability p ≥ O(ν² r² log(n)/n) and a hard-thresholding initialization under a weaker rate.
citing papers explorer
-
Geodesic Learning via Unsupervised Decision Forests
URerF uses unsupervised decision forests on sparse linear feature combinations to estimate geodesic distances robustly under high-dimensional noise, outperforming Isomap, UMAP, and FLANN on simulated and connectome data.
-
Provable Non-Convex Euclidean Distance Matrix Completion: Geometry, Reconstruction, and Robustness
Riemannian gradient descent on rank-r Gram matrices for EDMC achieves linear convergence with high probability for sampling probability p ≥ O(ν² r² log(n)/n) and a hard-thresholding initialization under a weaker rate.