PAC learning with generalized samples and an application to stochastic geometry

In this paper, we introduce an extension of the standard PAC learning model which allows the use of generalized samples. We view a generalized sample as a pair consisting of a functional on the concept class together with the value obtained by the functional operating on the unknown concept. It appears that this model can be applied to a number of problems in signal processing and geometric reconstruction to provide sample size bounds under a PAC criterion. We consider a specific application of the model to a problem of curve reconstruction, and discuss some connections with a result from stochastic geometry.

[1]  S. Sherman.  A comparison of linear measures in the plane , 1942 .

[2]  H. Steinhaus.  Length, shape and area , 1954 .

[3]  J. Lamperti.  ON CONVERGENCE OF STOCHASTIC PROCESSES , 1962 .

[4]  P. Moran.  Measuring the length of a curve , 1966 .

[5]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[6]  L. Santaló.  Integral geometry and geometric probability , 1976 .

[7]  S. Chern.  Review: Luis A. Santaló, Integral geometry and geometric probability , 1977 .

[8]  R. Dudley.  Central Limit Theorems for Empirical Measures , 1978 .

[9]  V. Vapnik,et al.  Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations , 1982 .

[10]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[11]  A. Baddeley.  Stochastic geometry and image analysis , 1984 .

[12]  David Haussler,et al.  Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension , 1986, STOC '86.

[13]  Steven Skiena,et al.  Geometric probing , 1988 .

[14]  Alon Itai,et al.  Learnability by fixed distributions , 1988, COLT '88.

[15]  S. Kulkarni,et al.  On metric entropy, Vapnik-Chervonenkis dimension, and learnability for a class of distributions , 1989 .

[16]  A. Aleksandrov,et al.  General theory of irregular curves , 1989 .

[17]  Jerry L. Prince,et al.  Reconstructing Convex Sets from Support Line Measurements , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  G. Wahba.  Spline models for observational data , 1990 .

[19]  Sanjeev R. Kulkarni,et al.  Convex set estimation from support line measurements and applications to target reconstruction from laser radar data , 1990, Photonics West - Lasers and Applications in Science and Engineering.

[20]  David Haussler,et al.  Decision Theoretic Generalizations of the PAC Learning Model , 1990, ALT.

[21]  Sanjeev R. Kulkarni,et al.  Problems of computational and informational complexity in machine vision and learning , 1991 .

[22]  W. Clem Karl,et al.  Reconstructing objects from projections , 1991 .

[23]  Sanjeev R. Kulkarni,et al.  Convex-polygon estimation from support-line measurements and applications to target reconstruction from laser-radar data , 1992 .

[24]  David Haussler,et al.  Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..