Fermat distance enables minimax-optimal weighted k-NN classifiers for high-dimensional semi-supervised learning with exponentially decaying estimation error from unlabeled data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
High-dimensional Semi-supervised Classification via the Fermat Distance
Fermat distance enables minimax-optimal weighted k-NN classifiers for high-dimensional semi-supervised learning with exponentially decaying estimation error from unlabeled data.