On the Relative Sizes of Learnable Sets

Abstract Measure and category (or rather, their recursion-theoretical counterparts) have been used in theoretical computer science to make precise the intuitive notion “for most of the recursive sets”. We use the notions of effective measure and category to discuss the relative sizes of inferrible sets, and their complements. We find that inferable sets become large rather quickly in the standard hierarchies of learnability. On the other hand, the complements of the learnable sets are all large.

[1]  Daniel N. Osherson,et al.  Aggregating Inductive Expertise , 1986, Inf. Control..

[2]  J. C. Oxtoby.  Measure and Category , 1971 .

[3]  Arun Sharma,et al.  Finite learning by a “team” , 1990, COLT '90.

[4]  Bala Kalyanasundaram,et al.  Capabilities of fallible FINite learning , 1993, COLT '93.

[5]  C. Schnorr.  Zufälligkeit und Wahrscheinlichkeit , 1971 .

[6]  Carl H. Smith,et al.  Probability and Plurality for Aggregations of Learning Machines , 1987, Inf. Comput..

[7]  Carl H. Smith,et al.  Co-learning of total recursive functions , 1994, COLT '94.

[8]  Manuel Blum,et al.  Toward a Mathematical Theory of Inductive Inference , 1975, Inf. Control..

[9]  R. Harré,et al.  Probability and Confirmation , 1970 .

[10]  Paul Young,et al.  An introduction to the general theory of algorithms , 1978 .

[11]  Carl H. Smith,et al.  Learning via queries , 1988, JACM.

[12]  John Case,et al.  Comparison of Identification Criteria for Machine Inductive Inference , 1983, Theor. Comput. Sci..

[13]  Stephen A. Fenner.  Notions of resource-bounded category and genericity , 1991, [1991] Proceedings of the Sixth Annual Structure in Complexity Theory Conference.

[14]  Carl H. Smith,et al.  Inductive Inference: Theory and Methods , 1983, CSUR.

[15]  É. Borel.  Leçons sur la théorie des fonctions , 2009 .

[16]  Leonard Pitt,et al.  Relations between probabilistic and team one-shot learners (extended abstract) , 1991, COLT '91.

[17]  Mahendran Velauthapillai.  Inductive inference with bounded number of mind changes , 1989, COLT '89.

[18]  H. Putnam.  Mathematics, Matter, And Method , 1975 .

[19]  John C. Oxtoby.  The Banach-Mazur Game , 1980 .

[20]  Carl H. Smith,et al.  The Power of Pluralism for Automatic Program Synthesis , 1982, JACM.

[21]  Bala Kalyanasundaram,et al.  Breaking the Probability 1/2 Barrier in FIN-Type Learning , 1995, J. Comput. Syst. Sci..

[22]  R. Soare.  Recursively enumerable sets and degrees , 1987 .

[23]  Carl H. Smith,et al.  A Recursive Introduction to the Theory of Computation , 1994, Graduate Texts in Computer Science.

[24]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[25]  D. C. Cooper,et al.  Theory of Recursive Functions and Effective Computability , 1969, The Mathematical Gazette.

[26]  Leonid Gurvits,et al.  A Note on VC-Dimension and Measure of Sets of Reals , 2000, Combinatorics, Probability and Computing.

[27]  Jack H. Lutz,et al.  The quantitative structure of exponential time , 1993, [1993] Proceedings of the Eigth Annual Structure in Complexity Theory Conference.

[28]  Bala Kalyanasundaram,et al.  Breaking the probability ½ barrier in FIN-type learning , 1992, COLT '92.

[29]  Jack H. Lutz.  Almost Everywhere High Nonuniform Complexity , 1992, J. Comput. Syst. Sci..

[30]  Kurt Mehlhorn.  On the Size of Sets of Computable Functions , 1973, SWAT.

[31]  Leonid Gurvits,et al.  A note on VC-dimension and measures of sets of reals , 1995, COLT '95.

[32]  C. Dilworth.  Probability and Confirmation , 1988 .

[33]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

[34]  Leonard Pitt,et al.  Probabilistic inductive inference , 1989, JACM.

[35]  Jr. Hartley Rogers.  Theory of Recursive Functions and Effective Computability , 1969 .