Sciweavers

970 search results - page 120 / 194
» On the relation between multi-instance learning and semi-sup...
Sort
View
COLT
2004
Springer
15 years 3 months ago
Sparseness Versus Estimating Conditional Probabilities: Some Asymptotic Results
One of the nice properties of kernel classifiers such as SVMs is that they often produce sparse solutions. However, the decision functions of these classifiers cannot always be u...
Peter L. Bartlett, Ambuj Tewari
CORR
2007
Springer
93views Education» more  CORR 2007»
14 years 10 months ago
Simultaneous Communication of Data and State
We consider the problem of transmitting data at rate R over a state dependent channel p(ylx, s) with the state information available at the sender and at the same time conveying th...
Thomas M. Cover, Young-Han Kim, Arak Sutivong
JMLR
2006
107views more  JMLR 2006»
14 years 10 months ago
Consistency of Multiclass Empirical Risk Minimization Methods Based on Convex Loss
The consistency of classification algorithm plays a central role in statistical learning theory. A consistent algorithm guarantees us that taking more samples essentially suffices...
Di-Rong Chen, Tao Sun
TIT
2008
66views more  TIT 2008»
14 years 9 months ago
State Amplification
We consider the problem of transmitting data at rate over a state-dependent channel with state information available at the sender and at the same time conveying the information ab...
Young-Han Kim, Arak Sutivong, Thomas M. Cover
TSP
2010
14 years 4 months ago
Testing stationarity with surrogates: a time-frequency approach
An operational framework is developed for testing stationarity relatively to an observation scale, in both stochastic and deterministic contexts. The proposed method is based on a ...
Pierre Borgnat, Patrick Flandrin, Paul Honeine, C&...