arXiv · cond-mat/0201256
Rigorous Bounds to Retarded Learning
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Arnaud Buhot, Mirta B. Gordon, Jean-Pierre Nadal. 2002-01-15. Rigorous Bounds to Retarded Learning. https://doi.org/10.1103/physrevlett.88.099801
Cite the original work for its findings. Save a collection to share your selection of sources.