Open AccessProceedings Article
Improving learning performance through rational resource allocation
Jonathan Gratch,Steve Chien,Gerald DeJong +2 more
- 05 Oct 1994
- pp 576-581
TL;DR: A heuristic learning algorithm is introduced that approximately solves the problem of efficient learning as a resource optimization problem and its performance improvements on synthetic and real-world problems are documented.
read more
Abstract: This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of efficient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
PALO: a probabilistic hill-climbing algorithm
TL;DR: A general algorithm is presented, palo, that returns an element that is, with provably high probability, essentially a local optimum and suggests approaches to solving the utility problem from explanation-based learning, the multiple extension problem from nonmonotonic reasoning and the tractability/completeness tradeoff problem from knowledge representation.
66
On the efficient allocation of resources for hypothesis evaluation: a statistical approach
TL;DR: Empirical results are presented that demonstrate the effectiveness of the hypothesis evaluation techniques for tuning system parameters in a NASA antenna scheduling application.
32
A quantitative study of hypothesis selection
Philip W. L. Fong
- 09 Jul 1995
TL;DR: This paper studies the minimization of sampling cost in hypothesis selection under a probably approximately optimal (PAO) learning framework, and proposes a novel family of learning algorithms, the γ-IE family, that explicitly trade off their exploration tendency with exploitation tendency.
31
•Proceedings Article
Sequential inductive learning
Jonathan Gratch
- 04 Aug 1996
TL;DR: The sequential inductive model is useful as a method for determining a sufficient sample size for inductive learning and as such, is relevant to learning problems where the preponderance of data or the cost of gathering data precludes the use of traditional methods.
20
•Proceedings Article
A Decision-theoretic Approach to Adaptive Problem Solving
Jonathan Gratch,Gerald DeJong,N. Mathews +2 more
- 01 Jan 1994
TL;DR: In this paper, the authors develop a formal characterization of the utility problem and introduce COMPOSER, a statistically rigorous approach to this problem, which is successfully applied to learning heuristics for planning and scheduling systems.
16
References
A theory of the learnable
Leslie G. Valiant
- 05 Nov 1984
TL;DR: This paper regards learning as the phenomenon of knowledge acquisition in the absence of explicit programming, and gives a precise methodology for studying this phenomenon from a computational viewpoint.
•Book
Introduction to Mathematical Statistics
Robert V. Hogg,Joseph W. McKean,Allen T. Craig +2 more
- 01 Jan 1959
TL;DR: In this article, the authors present a list of common distributions of probability and distribution of likelihood for Bayesian models. But they do not discuss the relation between distributions and normal models.
3K
Introduction to Mathematical Statistics
David G. Kendall
- 01 Nov 1947
TL;DR: Paul G. Hoel's “Introduction to Mathematical Statistics” seems to me to be an excellent work, and if only it can become generally available it may have a most favourable effect on the situation just described.
1.7K
Do the right thing: studies in limited rationality
Stuart Russell,Eric H. Wefald +1 more
- 01 Sep 1991
TL;DR: Limited rationality execution architectures for decision procedures metareasoning architecture rational metareASONing application to game playing application to problem solving search learning the value of computation toward limited rational agents.
395
•Proceedings Article
Rationality and its roles in reasoning
Jon Doyle
- 29 Jul 1990
TL;DR: This work surveys the growing literature on how the basic notions of probability, utility, and rational choice, coupled with practical limitations on information and resources, influence the design and analysis of reasoning and representation systems.
160