𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A sufficient condition for polynomial distribution-dependent learnability

✍ Scribed by Martin Anthony; John Shawe-Taylor

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
741 KB
Volume
77
Category
Article
ISSN
0166-218X

No coin nor oath required. For personal study only.

✦ Synopsis

We investigate upper bounds on the sample-size sufficient for 'solid' learnability with respect to a probability distribution. Extending analysis of Ben-David et al. (1989, 1995) and Bendek and Itai (1991) we obtain a sufficient condition for feasible (polynomially bounded) sample-size bounds for distribution-specific (solid) learnability.

πŸ“œ SIMILAR VOLUMES

A sufficient condition for invexity
A sufficient condition for invexity
✍ Morgan A Hanson; Norma G Rueda πŸ“‚ Article πŸ“… 1989 πŸ› Elsevier Science 🌐 English βš– 214 KB
Sufficient algebraic conditions for stab
Sufficient algebraic conditions for stability of cones of polynomials
✍ B. Aguirre; C. Ibarra; R. SuΓ‘rez πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 124 KB

In this paper a su cient condition for a cone of polynomials to be Hurwitz is established. Such condition is a matrix inequality, which gives a simple algebraic test for the stability of rays of polynomials. As an application to stable open-loop systems, a cone of gains c such that the function u =