21 search results - page 1 / 5 » Suboptimality of Penalized Empirical Risk Minimization in Cl... |
COLT
2007
Springer
13 years 11 months ago
2007
Springer
JMLR
2010
12 years 11 months ago
2010
Concentration inequalities that incorporate variance information (such as Bernstein's or Bennett's inequality) are often significantly tighter than counterparts (such as...
JMLR
2006
13 years 4 months ago
2006
The consistency of classification algorithm plays a central role in statistical learning theory. A consistent algorithm guarantees us that taking more samples essentially suffices...
JMLR
2010
12 years 11 months ago
2010
In this paper, we investigate the problem of binary classification with a reject option in which one can withhold the decision of classifying an observation at a cost lower than t...
COLT
2004
Springer
13 years 8 months ago
2004
Springer
This paper introduces a new method using dyadic decision trees for estimating a classification or a regression function in a multiclass classification problem. The estimator is bas...