Property testing: a learning theory perspective

Authors:
Dana Ron
Affiliations:
Department of EE-Systems, Tel-Aviv University, Ramat Aviv, Israel
Venue:
COLT'07 Proceedings of the 20th annual conference on Learning theory
Year:
2007

Citing 11
Cited 1

Self-testing/correcting with applications to numerical problems

Journal of Computer and System Sciences - Special issue: papers from the 22nd ACM symposium on the theory of computing, May 14–16, 1990
Toward Efficient Agnostic Learning

Machine Learning - Special issue on computational learning theory, COLT'92
Property testing and its connection to learning and approximation

Journal of the ACM (JACM)
Spot-checkers

Journal of Computer and System Sciences - 30th annual ACM symposium on theory of computing
Testing problems with sublearning sample complexity

Journal of Computer and System Sciences
Robust Characterizations of Polynomials withApplications to Program Testing

SIAM Journal on Computing
Testing Basic Boolean Formulae

SIAM Journal on Discrete Mathematics
Testing of Clustering

SIAM Journal on Discrete Mathematics
Testing juntas

Journal of Computer and System Sciences - Special issue on FOCS 2002
A combinatorial characterization of the testable graph properties: it's all about regularity

Proceedings of the thirty-eighth annual ACM symposium on Theory of computing
Information theory in property testing and monotonicity testing in higher dimension

Information and Computation

Testing halfspaces

SODA '09 Proceedings of the twentieth Annual ACM-SIAM Symposium on Discrete Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

Property testing [15,9] is the study of the following class of problems. Given the ability to perform local queries concerning a particular object (e.g., a function, or a graph), the problem is to determine whether the object has a predetermined global property (e.g., linearity or bipartiteness), or differs significantly from any object that has the property. In the latter case we say it is far from (having) the property. The algorithm is allowed a probability of failure, and typically it inspects only a small part of the whole object.