Part of Advances in Neural Information Processing Systems 17 (NIPS 2004)
Yoshua Bengio, Martin Monperrus
We claim and present arguments to the effect that a large class of man- ifold learning algorithms that are essentially local and can be framed as kernel learning algorithms will suffer from the curse of dimensionality, at the dimension of the true underlying manifold. This observation sug- gests to explore non-local manifold learning algorithms which attempt to discover shared structure in the tangent planes at different positions. A criterion for such an algorithm is proposed and experiments estimating a tangent plane prediction function are presented, showing its advantages with respect to local manifold learning algorithms: it is able to general- ize very far from training data (on learning handwritten character image rotations), where a local non-parametric method fails.