Consistency of Lipschitz learning with infinite unlabeled data and finite labeled data — mentioned by WAMoezart

Tue, 07 Dec 2021 23:12:33 GMT

A simple way to do SSL with not enough data is Lipschitz learning. It avoids the necessity for pseudo-labeling and computes an absolutely minimizing Lipschitz extension of the labels instead. https://arxiv.org/abs/2111.12370 https://arxiv.org/abs/2012.03772 https://arxiv.org/abs/1901.05031 https://arxiv.org/abs/1710.10364

Paper and discussion history. A mention is not an endorsement.

Consistency of Lipschitz learning with infinite unlabeled data and finite labeled data · HackerPapers discussions

Consistency of Lipschitz learning with infinite unlabeled data and finite labeled data — mentioned by WAMoezart