Attribute-Efficient Learning in Query and Mistake-Bound Models
Reads0
Chats0
TLDR
This work considers a variant of the membership query model in which the learning algorithm is given as input the number of relevant variables of the target function, and shows that in this model, any projection and embedding closed class of functions that can be learned in polynomial time can be learning attribute-efficiently in poynomial time.About:
This article is published in Journal of Computer and System Sciences.The article was published on 1998-06-01 and is currently open access. It has received 26 citations till now. The article focuses on the topics: Time complexity.read more
Citations
More filters
Journal ArticleDOI
Measuring the impact of data mining on churn management
TL;DR: A customer relationship management framework based on the integration of the electronic channel is presented, able to prefigure the possible impact induced by the ongoing data mining enhancements on churn management and on the decision‐making process.
Journal ArticleDOI
Learning conditional preference networks
Frédéric Koriche,Bruno Zanuttini +1 more
TL;DR: This model shows that acyclic CP-nets are not learnable with equivalence queries alone, even if the examples are restricted to swaps for which dominance testing takes linear time, and reveals that active queries are required for efficiently learningCP-nets in large multi-attribute domains.
Journal ArticleDOI
Projection Learning
TL;DR: A method of combining learning algorithms is described that preserves attribute-efficiency and yields learning algorithms that require a number of examples that is polynomial in the number of relevant variables and logarithmic in the total number of variables.
Journal ArticleDOI
Finding Essential Attributes from Binary Data
TL;DR: This paper proposes several measures of separation (real valued set functions over the subsets of attributes), formulate optimization models for finding the smallest subsets maximizing these measures, and devise efficient heuristic algorithms to solve these (typically NP-hard) optimization problems.
Proceedings ArticleDOI
Computational sample complexity and attribute-efficient learning
TL;DR: It is demonstrated that even for simple concept classes, an inherent tradeoff can exist between running time and sample complexity, and the first result which shows that attribute-efficient learning can be computationally hard is shown.
References
More filters
Book
Randomized Algorithms
TL;DR: This book introduces the basic concepts in the design and analysis of randomized algorithms and presents basic tools such as probability theory and probabilistic analysis that are frequently used in algorithmic applications.
Lecture Notes in Artificial Intelligence
P. Brezillon,P. Bouquet +1 more
TL;DR: The topics in LNAI include automated reasoning, automated programming, algorithms, knowledge representation, agent-based systems, intelligent systems, expert systems, machine learning, natural-language processing, machine vision, robotics, search systems, knowledge discovery, data mining, and related programming languages.
Journal ArticleDOI
Queries and Concept Learning
TL;DR: This work considers the problem of using queries to learn an unknown concept, and several types of queries are described and studied: membership, equivalence, subset, superset, disjointness, and exhaustiveness queries.
Journal ArticleDOI
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm
TL;DR: This work presents one such algorithm that learns disjunctive Boolean functions, along with variants for learning other classes of Boolean functions.
Journal ArticleDOI
Parity, circuits and the polynomial time hierarchy
TL;DR: A super-polynomial lower bound is given for the size of circuits of fixed depth computing the parity function and connections are given to the theory of programmable logic arrays and to the relativization of the polynomial-time hierarchy.