๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Learning Random Log-Depth Decision Trees under Uniform Distribution

โœ Scribed by Jackson, Jeffrey C.; Servedio, Rocco A.


Book ID
118181317
Publisher
Society for Industrial and Applied Mathematics
Year
2005
Tongue
English
Weight
268 KB
Volume
34
Category
Article
ISSN
0097-5397

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


An O(nlog log n) Learning Algorithm for
โœ Y. Mansour ๐Ÿ“‚ Article ๐Ÿ“… 1995 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 571 KB

We show that a DNF with terms of size at most \(d\) can be approximated by a function at most \(d^{O(d \log 1 / \epsilon)}\) nonzero Fourier coefficients such that the expected error squared, with respect to the uniform distribution, is at most \(\epsilon\). This property is used to derive a learnin