### Abstract

In the framework of PAC-learning model, relationships between learning processes and information compressing processes are investigated. Information compressing processes are formulated as weak Occam algorithms. A weak Occam algorithm is a deterministic polynomial time algorithm that, when given m examples of unknown function, outputs, with high probability, a representation of a function that is consistent with the examples and belongs to a function class with complexity o(m). It has been shown that a weak Occam algorithm is also a consistent PAC-learning algorithm. In this extended abstract, it is shown that the converse does not hold by giving a PAC-learning algorithm that is not a weak Occam algorithm, and also some natural properties, called conservativeness and monotonicity, for learning algorithms that might help the converse hold are given. In particular, the conditions that make a conservative PAC-learning algorithm a weak Occam algorithm are given, and it is shown that, under some natural conditions, a monotone PAC-learning algorithm for a hypothesis class can be transformed to a weak Occam algorithm without changing the hypothesis class.

Original language | English |
---|---|

Title of host publication | Proc 6 Annu ACM Conf Comput Learn Theory |

Editors | Anon |

Publisher | Publ by ACM |

Pages | 377-383 |

Number of pages | 7 |

ISBN (Print) | 0897916115 |

Publication status | Published - 1993 |

Externally published | Yes |

Event | Proceedings of the 6th Annual ACM Conference on Computational Learning Theory - Santa Cruz, CA, USA Duration: Jul 26 1993 → Jul 28 1993 |

### Other

Other | Proceedings of the 6th Annual ACM Conference on Computational Learning Theory |
---|---|

City | Santa Cruz, CA, USA |

Period | 7/26/93 → 7/28/93 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Engineering(all)

### Cite this

*Proc 6 Annu ACM Conf Comput Learn Theory*(pp. 377-383). Publ by ACM.

**Conservativeness and monotonicity for learning algorithms.** / Takimoto, Eiji; Maruoka, Akira.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*Proc 6 Annu ACM Conf Comput Learn Theory.*Publ by ACM, pp. 377-383, Proceedings of the 6th Annual ACM Conference on Computational Learning Theory, Santa Cruz, CA, USA, 7/26/93.

}

TY - GEN

T1 - Conservativeness and monotonicity for learning algorithms

AU - Takimoto, Eiji

AU - Maruoka, Akira

PY - 1993

Y1 - 1993

N2 - In the framework of PAC-learning model, relationships between learning processes and information compressing processes are investigated. Information compressing processes are formulated as weak Occam algorithms. A weak Occam algorithm is a deterministic polynomial time algorithm that, when given m examples of unknown function, outputs, with high probability, a representation of a function that is consistent with the examples and belongs to a function class with complexity o(m). It has been shown that a weak Occam algorithm is also a consistent PAC-learning algorithm. In this extended abstract, it is shown that the converse does not hold by giving a PAC-learning algorithm that is not a weak Occam algorithm, and also some natural properties, called conservativeness and monotonicity, for learning algorithms that might help the converse hold are given. In particular, the conditions that make a conservative PAC-learning algorithm a weak Occam algorithm are given, and it is shown that, under some natural conditions, a monotone PAC-learning algorithm for a hypothesis class can be transformed to a weak Occam algorithm without changing the hypothesis class.

AB - In the framework of PAC-learning model, relationships between learning processes and information compressing processes are investigated. Information compressing processes are formulated as weak Occam algorithms. A weak Occam algorithm is a deterministic polynomial time algorithm that, when given m examples of unknown function, outputs, with high probability, a representation of a function that is consistent with the examples and belongs to a function class with complexity o(m). It has been shown that a weak Occam algorithm is also a consistent PAC-learning algorithm. In this extended abstract, it is shown that the converse does not hold by giving a PAC-learning algorithm that is not a weak Occam algorithm, and also some natural properties, called conservativeness and monotonicity, for learning algorithms that might help the converse hold are given. In particular, the conditions that make a conservative PAC-learning algorithm a weak Occam algorithm are given, and it is shown that, under some natural conditions, a monotone PAC-learning algorithm for a hypothesis class can be transformed to a weak Occam algorithm without changing the hypothesis class.

UR - http://www.scopus.com/inward/record.url?scp=0027838951&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027838951&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0897916115

SP - 377

EP - 383

BT - Proc 6 Annu ACM Conf Comput Learn Theory

A2 - Anon, null

PB - Publ by ACM

ER -