Sciweavers

597 search results - page 21 / 120
» Dominating Distributions and Learnability
Sort
View
QEST
2006
IEEE
15 years 11 months ago
Measuring and Modeling of Application Flow Length in Commercial GPRS Networks
New mobile access networks provide reasonable high bandwidth to allow true internet access. This paper models two dominant applications of those networks. One application, WAP, is...
Roger Kalden, Boudewijn R. Haverkort
STOC
1994
ACM
128views Algorithms» more  STOC 1994»
15 years 9 months ago
Weakly learning DNF and characterizing statistical query learning using Fourier analysis
We present new results on the well-studied problem of learning DNF expressions. We prove that an algorithm due to Kushilevitz and Mansour [13] can be used to weakly learn DNF form...
Avrim Blum, Merrick L. Furst, Jeffrey C. Jackson, ...
COLT
2006
Springer
15 years 8 months ago
Efficient Learning Algorithms Yield Circuit Lower Bounds
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
Lance Fortnow, Adam R. Klivans
155
Voted
JMLR
2006
109views more  JMLR 2006»
15 years 5 months ago
Some Discriminant-Based PAC Algorithms
A classical approach in multi-class pattern classification is the following. Estimate probability distributions that generated the observations for each label class, and then labe...
Paul W. Goldberg
120
Voted
DLT
2003
15 years 6 months ago
Frequency of Symbol Occurrences in Simple Non-primitive Stochastic Models
We study the random variable Yn representing the number of occurrences of a given symbol in a word of length n generated at random. The stochastic model we assume is a simple non-e...
Diego de Falco, Massimiliano Goldwurm, Violetta Lo...