Mihir Bellare
ABSTRACT
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 particular, we present polynomial time algorithms for learning O(log n) clause DNF formulas and various classes of decision trees, all under the uniform distribution with membership queries.
- Be.M. BELLARE. The Spectral Norm of Finite Functions. MIT Laboratory for Computer Science Technical Report MIT/LCS/TR- 495, February 1991. Google Scholar
Digital Library
- BR.A. BLUM AND S. RUDICH. Fast Learning of k-term DNF formulas with queries. Proceedings of the ~.tth Annual ACM Symposium on the Theory of Computing, ACM (1992). Google ScholarDigital Library
- Br.J. BaUCK. Harmonic Analysis of Polynomial Threshold Functions. SIAM J. Discrete Math. 3(2), 168-177 (1990).Google ScholarCross Ref
- BS.J. BgUCK AND R. SMOLr. NSKY. Polynomial Threshold Functions, AC~ Functions, and Spectral Norms. Proceedings of the 31st Annual IEEE Symposium on the Foundations of Computer Sczence, IEEE (1990).Google Scholar
- FJS.M. FUI~ST, J. JACKSON AND S. SMITH. Learning AC~ Functions Sampled under Mutually Independent Distributions. Manuscript (October 1990).Google Scholar
- HMPST.A. HAJNAL, W. MAASS, P. PUDLAK, M. SZEGEDY AND G. TURAN. Threshold Circuits of Bounded Depth. Proceedings of the ~8th Annual IEEE Symposium ou the Foundations of Computer Science, IEEE (1987).Google Scholar
- KKL.J. KAHN, G. KALAI AND N. LINIAL. The Influence of Variables on Boolean Functions. Proceedings of the ~9th Annual IEEE Symposium on the Foundations of Computer Science, IEEE (1988).Google Scholar
- KM.E. KUSHILEVITZ AND Y. MANSOUR. Learning Decision Trees using the Fourier Spectrum. Proceedings of the 23rd Annual ACM Symposium on the Theory of Computing, ACM (1991). Google ScholarDigital Library
- LMN.N. LINIAL, Y. MANSOUR AND N. NISAN. Constant Depth Circuits, Fourier Transform, and Learnability. Proceedings of the 30th Annual IEEE Symposium on the Foundatwns of Computer Science, IEEE (1989).Google ScholarDigital Library
- SB.K. SIu AND J. BaUCK. On the Power of Threshold Circuits with Small Weights. Manuscript.Google Scholar
- Va.L. VALIANT. A Theory of the Learnable. Communications of the ACM 27(11), 1134- 1142 (1984). Google ScholarDigital Library
- Ve.K. VERBEURGT. Learning DNF under the uniform distribution in polynomial time. Proceedings of the Second Annual Workshop on Computational Learning Theory, Morgan Kaufmann Publishers Inc. (1989).Google Scholar
Index Terms
- A technique for upper bounding the spectral norm with applications to learning
Recommendations
Bounds on the Spectral Norm and the Nuclear Norm of a Tensor Based on Tensor Partitions
It is known that computing the spectral norm and the nuclear norm of a tensor is NP-hard in general. In this paper, we provide neat bounds for the spectral norm and the nuclear norm of a tensor based on tensor partitions. The spectral norm (respectively, ...
Upper bounding rainbow connection number by forest number
AbstractA path in an edge-colored graph is rainbow if no two edges of it are colored the same, and the graph is rainbow-connected if there is a rainbow path between each pair of its vertices. The minimum number of colors needed to rainbow-...
A Dual Generalized Upper Bounding Technique
A Generalized Upper Bounding technique, similar to that introduced by Dantzig and Van Slyke [Dantzig, G. B., Van Slyke, R. M., 1967. Generalized upper bounding techniques. Journal of Computer and System Sciences . Vol. 1 pp. 213--226.], for solving ...
Comments