Arnaud Buhot, Mirta B. Gordon, Jean-Pierre Nadal
Published 2002-01-15Version 1
We show that the lower bound to the critical fraction of data needed to infer (learn) the orientation of the anisotropy axis of a probability distribution, determined by Herschkowitz and Opper [Phys.Rev.Lett. 86, 2174 (2001)], is not always valid. If there is some structure in the data along the anisotropy axis, their analysis is incorrect, and learning is possible with much less data points.
Comments: 1 page, 1 figure. Comment accepted for publication in Physical Review Letters
On the Dynamics of Inference and Learning
The probability distribution of the conductance in anisotropic systems
Possible Connection between the Optimal Path and Flow in Percolation Clusters
