A Technique for Upper Bounding the Spectral Norm with Applications to Learning

@inproceedings{Bellare1992ATF,
  title={A Technique for Upper Bounding the Spectral Norm with Applications to Learning},
  author={Mihir Bellare},
  booktitle={COLT},
  year={1992}
}
We present a general technique to upper bound the spectral norm of an arbitrary function. At the heart of our technique is a theorem which shows how to obtain an upper bound on the spectral norm of a decision tree given the spectral norms of the functions in the nodes of this tree. The theorem applies to trees whose nodes may compute any boolean functions. Applications are to the design of efficient learning algorithms and the construction of small depth threshold circuits (or neural nets). In… CONTINUE READING

Similar Papers

Figures and Topics from this paper.

Citations

Publications citing this paper.