Download:
|
by William W. Cohen, Russell Greiner, Dale Schuurmans
Proceedings of Computational Learning Theory and 'Natural' Learning Systems
http://www-2.cs.cmu.edu/~wcohen/postscript/clnl-91.ps
Add To MetaCart
Abstract:
Abstract: Many learning tasks involve searching through a discrete space of performance elements, seeking an element whose future utility is expected to be high. As the task of finding the global optimum is often intractable, many practical learning systems use simple forms of hill-climbing to find a locally optimal element. However, hill-climbing can be complicated by the fact that the utility value of a performance element can depend on the distribution of problems, which typically is unknown. This paper formulates the problem of performing hill-climbing search in settings where the required utility values can only be estimated on the basis of their performance on random test cases. We present and prove correct an algorithm that returns a performance element that is arbitrarily close to a local optimum with arbitrarily high probability.
Citations
|
2489
|
Induction of Decision Trees
– Quinlan
- 1986
|
|
1364
|
A theory of the learnable
– Valiant
- 1984
|
|
1154
|
Random graphs
– Bollobás
- 1985
|
|
637
|
Estinwtion of Dependences Based on Empirical Data
– Vapnik
- 1982
|
|
540
|
Soar: An architecture for general intelligence
– Laird, Newell, et al.
- 1987
|
|
481
|
An analysis of time-dependent planning
– Dean, Boddy
- 1988
|
|
427
|
A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations
– Chernoff
- 1995
|
|
322
|
Decision theoretic generalization of the PAC model for neural net and other learning applications
– Haussler
- 1992
|
|
273
|
Connectionist learning procedures
– Hinton
- 1989
|
|
219
|
Quantifying Inductive Bias: AI Learning Algorithms and Valiant’s Learning Framework
– Haussler
- 1988
|
|
210
|
Solving TimeDependent Planning Problems
– Boddy, Dean
- 1989
|
|
109
|
Learning Search Control Knowledge: An Explanation–Based Approach
– Minton
- 1988
|
|
72
|
A learning apprentice for VLSI design
– Mitchell, Mahadevan, et al.
- 1985
|
|
47
|
A Statistical Approach to Solving the EBL Utility Problem
– Greiner, Jurisica
- 1992
|
|
34
|
Finding the optimal derivation strategy in a redundant knowledge base
– Greiner
- 1991
|
|
34
|
Defining operationality for explanation-based learning
– Keller
- 1988
|
|
23
|
Models of Learning Systems
– Buchanan, Mitchell, et al.
- 1978
|
|
17
|
Classification and Regression Trees
– Stone
- 1984
|
|
15
|
Probabilistic hill climbing : Theory and applications
– Greiner
- 1992
|
|
12
|
A hybrid approach to guaranteed effective control strategies
– Gratch, Dejong
- 1991
|
|
8
|
AAAI workshop on Explanation-Based Learning. Sponsored by AAAI
– DeJong
- 1988
|
|
7
|
An average case complexity analysis of the satisfiability problem
– Goldberg
- 1979
|
