Sciweavers

88 search results - page 1 / 18
» On Using Extended Statistical Queries to Avoid Membership Qu...
Sort
View
COLT
2001
Springer
13 years 9 months ago
On Using Extended Statistical Queries to Avoid Membership Queries
The Kushilevitz-Mansour (KM) algorithm is an algorithm that finds all the “large” Fourier coefficients of a Boolean function. It is the main tool for learning decision trees ...
Nader H. Bshouty, Vitaly Feldman
JCSS
2007
85views more  JCSS 2007»
13 years 4 months ago
A general dimension for query learning
We introduce a combinatorial dimension that characterizes the number of queries needed to exactly (or approximately) learn concept classes in various models. Our general dimension...
José L. Balcázar, Jorge Castro, Davi...
ISTCS
1997
Springer
13 years 8 months ago
Learning with Queries Corrupted by Classification Noise
Kearns introduced the "statistical query" (SQ) model as a general method for producing learning algorithms which are robust against classification noise. We extend this ...
Jeffrey C. Jackson, Eli Shamir, Clara Shwartzman
STOC
1994
ACM
128views Algorithms» more  STOC 1994»
13 years 8 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, ...
SIGIR
2008
ACM
13 years 4 months ago
Learning query intent from regularized click graphs
This work presents the use of click graphs in improving query intent classifiers, which are critical if vertical search and general-purpose search services are to be offered in a ...
Xiao Li, Ye-Yi Wang, Alex Acero