Sciweavers

2767 search results - page 333 / 554
» Universal Exponentiation Algorithm
Sort
View
93
Voted
ALT
2010
Springer
15 years 4 months ago
Approximation Stability and Boosting
Stability has been explored to study the performance of learning algorithms in recent years and it has been shown that stability is sufficient for generalization and is sufficient ...
Wei Gao, Zhi-Hua Zhou
120
Voted
AAAI
2010
15 years 3 months ago
Propagating Conjunctions of AllDifferent Constraints
We study propagation algorithms for the conjunction of two ALLDIFFERENT constraints. Solutions of an ALLDIFFERENT constraint can be seen as perfect matchings on the variable/value...
Christian Bessiere, George Katsirelos, Nina Narody...
107
Voted
NIPS
2008
15 years 3 months ago
Linear Classification and Selective Sampling Under Low Noise Conditions
We provide a new analysis of an efficient margin-based algorithm for selective sampling in classification problems. Using the so-called Tsybakov low noise condition to parametrize...
Giovanni Cavallanti, Nicolò Cesa-Bianchi, C...
99
Voted
SDM
2008
SIAM
140views Data Mining» more  SDM 2008»
15 years 3 months ago
Large-Scale Many-Class Learning
In many multiclass learning scenarios, the number of classes is relatively large (thousands,...), or the space and time efficiency of the learning system can be crucial. We invest...
Omid Madani, Michael Connor
137
Voted
UAI
2008
15 years 3 months ago
Tightening LP Relaxations for MAP using Message Passing
Linear Programming (LP) relaxations have become powerful tools for finding the most probable (MAP) configuration in graphical models. These relaxations can be solved efficiently u...
David Sontag, Talya Meltzer, Amir Globerson, Tommi...