CVPR
2011
IEEE
13 years 4 months ago
2011
IEEE
A new family of boosting algorithms, denoted TaylorBoost, is proposed. It supports any combination of loss function and first or second order optimization, and includes classical...
TNN
2010
13 years 7 months ago
2010
Clustering using the Hilbert Schmidt independence criterion (CLUHSIC) is a recent clustering algorithm that maximizes the dependence between cluster labels and data observations ac...
SAC
2010
ACM
13 years 7 months ago
2010
ACM
The label switching problem is caused by the likelihood of a Bayesian mixture model being invariant to permutations of the labels. The permutation can change multiple times betwee...
INTERSPEECH
2010
13 years 7 months ago
2010
This paper describes improvements in a search error risk minimization approach to fast beam search for speech recognition. In our previous work, we proposed this approach to reduc...
ICDM
2009
IEEE
13 years 10 months ago
2009
IEEE
This paper presents a simple but powerful extension of the maximum margin clustering (MMC) algorithm that optimizes multivariate performance measure specifically defined for clust...
COLT
2010
Springer
13 years 10 months ago
2010
Springer
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
TIT
1998
14 years 2 days ago
1998
Abstract— We consider adaptive sequential prediction of arbitrary binary sequences when the performance is evaluated using a general loss function. The goal is to predict on each...
ML
2002
ACM
14 years 3 days ago
2002
ACM
In this paper, we elaborate on the well-known relationship between Gaussian Processes (GP) and Support Vector Machines (SVM) under some convex assumptions for the loss functions. ...
FUIN
2006
14 years 13 days ago
2006
In this paper we derive the bounds for Validation (known also as Hold-Out Estimate and Train-and-Test Method). We present the best possible bound in the case of 0-1 valued loss fun...
ADCM
2007
14 years 17 days ago
2007
In this paper, we are interested in the analysis of regularized online algorithms associated with reproducing kernel Hilbert spaces. General conditions on the loss function and st...