no code implementations • NeurIPS 2010 • Hariharan Narayanan, Sanjoy Mitter
Given upper bounds on the dimension, volume, and curvature, we show that Empirical Risk Minimization can produce a nearly optimal manifold using a number of random samples that is {\it independent} of the ambient dimension of the space in which data lie.
no code implementations • NeurIPS 2010 • Peter Jones, Venkatesh Saligrama, Sanjoy Mitter
Experts (human or computer) are often required to assess the probability of uncertain events.