Learning an Optimally Accurate Representational System
- Russ Greiner, Dept of Computing Science; PI of AICML
- Dale Schuurmans, AICML
A default theory can sanction different, mutually incompatible, answers to certain queries. We can identify each such theory with a set of related credulous theories, each of which produces but a single response to each query, by imposing a total ordering on the defaults. Our goal is to identify the credulous theory with optimal "expected accuracy" averaged over the natural distribution of queries in the domain. There are two obvious complications: First, the expected accuracy of a theory depends on the query distribution, which is usually not known. Second, the task of identifying the optimal theory, even given that distribution information, is intractable. This paper presents a method, OptAcc, that side-steps these problems by using a set of samples to estimate the unknown distribution, and by hill-climbing to a local optimum. In particular, given any error and confidence parameters epsilon, delta>0, OptAcc produces a theory whose expected accuracy is, with probability at least 1-delta, within epsilon of a local optimum.
Citation
R. Greiner, D. Schuurmans. "Learning an Optimally Accurate Representational System". ECAI Workshop on Theoretical Foundations of Knowledge Representation and Reasoning, Springer Verlag, August 1993.| Keywords: | machine learning, accurate, PAC, PALO |
| Category: | In Workshop |
BibTeX
@misc{Greiner+Schuurmans:93,
author = {Russ Greiner and Dale Schuurmans},
title = {Learning an Optimally Accurate Representational System},
booktitle = {ECAI Workshop on Theoretical Foundations of Knowledge
Representation and Reasoning, Springer Verlag},
year = 1993,
}Last Updated: August 16, 2007Submitted by Russ Greiner
