Sciweavers

701 search results - page 41 / 141
» Self Bounding Learning Algorithms
Sort
View
JMLR
2011
137views more  JMLR 2011»
13 years 4 months ago
Online Learning in Case of Unbounded Losses Using Follow the Perturbed Leader Algorithm
In this paper the sequential prediction problem with expert advice is considered for the case where losses of experts suffered at each step cannot be bounded in advance. We presen...
Vladimir V. V'yugin
IJIS
2008
123views more  IJIS 2008»
13 years 9 months ago
Algorithms of nonlinear document clustering based on fuzzy multiset model
Abstract: Fuzzy multiset is applicable as a model of information retrieval because it has the mathematical structure which expresses the number and the degree of attribution of an ...
Kiyotaka Mizutani, Ryo Inokuchi, Sadaaki Miyamoto
FOCS
2002
IEEE
14 years 2 months ago
Learning a Hidden Matching
We consider the problem of learning a matching (i.e., a graph in which all vertices have degree 0 or 1) in a model where the only allowed operation is to query whether a set of ve...
Noga Alon, Richard Beigel, Simon Kasif, Steven Rud...
COLT
2006
Springer
14 years 1 months ago
Online Learning Meets Optimization in the Dual
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Shai Shalev-Shwartz, Yoram Singer
ICPR
2004
IEEE
14 years 10 months ago
Relevant Linear Feature Extraction Using Side-information and Unlabeled Data
"Learning with side-information" is attracting more and more attention in machine learning problems. In this paper, we propose a general iterative framework for relevant...
Changshui Zhang, Fei Wu, Yonglei Zhou