๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Sample Complexity for Computational Classification Problems

โœ Scribed by Daniil Ryabko


Publisher
Springer
Year
2007
Tongue
English
Weight
182 KB
Volume
49
Category
Article
ISSN
0178-4617

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


Complexity of classification problems
โœ I. V. Sergienko; A. M. Gupal; S. V. Pashko ๐Ÿ“‚ Article ๐Ÿ“… 1996 ๐Ÿ› Springer US ๐ŸŒ English โš– 650 KB
Computational Sample Complexity and Attr
โœ Rocco A. Servedio ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 221 KB

Two fundamental measures of the efficiency of a learning algorithm are its running time and the number of examples it requires (its sample complexity). In this paper we demonstrate that even for simple concept classes, an inherent tradeoff can exist between running time and sample complexity. We pre

Testing Problems with Sublearning Sample
โœ Michael Kearns; Dana Ron ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 249 KB

We study the problem of determining, for a class of functions H, whether an unknown target function f is contained in H or is ``far'' from any function in H. Thus, in contrast to problems of learning, where we must construct a good approximation to f in H on the basis of sample data, in problems of