Sciweavers

180 search results - page 3 / 36
» Improved bounds on the sample complexity of learning
Sort
View
CORR
2010
Springer
94views Education» more  CORR 2010»
13 years 7 months ago
Tight Sample Complexity of Large-Margin Learning
We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the -adapted-dimension, which...
Sivan Sabato, Nathan Srebro, Naftali Tishby
TEC
2012
197views Formal Methods» more  TEC 2012»
11 years 10 months ago
Improving Generalization Performance in Co-Evolutionary Learning
Recently, the generalization framework in co-evolutionary learning has been theoretically formulated and demonstrated in the context of game-playing. Generalization performance of...
Siang Yew Chong, Peter Tino, Day Chyi Ku, Xin Yao
NIPS
2004
13 years 8 months ago
Analysis of a greedy active learning strategy
act out the core search problem of active learning schemes, to better understand the extent to which adaptive labeling can improve sample complexity. We give various upper and low...
Sanjoy Dasgupta
JMLR
2006
118views more  JMLR 2006»
13 years 7 months ago
Learning Factor Graphs in Polynomial Time and Sample Complexity
We study the computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded degree...
Pieter Abbeel, Daphne Koller, Andrew Y. Ng
ICML
2008
IEEE
14 years 8 months ago
On multi-view active learning and the combination with semi-supervised learning
Multi-view learning has become a hot topic during the past few years. In this paper, we first characterize the sample complexity of multi-view active learning. Under the expansion...
Wei Wang, Zhi-Hua Zhou