Parametric estimation and tests through divergences and the duality technique
Journal of Multivariate Analysis
Surrogate regret bounds for proper losses
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
IEEE Transactions on Information Theory
Sided and symmetrized Bregman centroids
IEEE Transactions on Information Theory
Hilbert Space Embeddings and Metrics on Probability Measures
The Journal of Machine Learning Research
A study on invariance of f-divergence and its application to speech recognition
IEEE Transactions on Signal Processing
Dual divergence estimators and tests: Robustness results
Journal of Multivariate Analysis
On Pinsker's and Vajda's type inequalities for Csiszár's f-divergences
IEEE Transactions on Information Theory
Estimating divergence functionals and the likelihood ratio by convex risk minimization
IEEE Transactions on Information Theory
Investigating sequential patterns of DNS usage and its applications
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications: Part I
Divergence-based vector quantization
Neural Computation
International Journal of Approximate Reasoning
Unsupervised clustering of multidimensional distributions using earth mover distance
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Information, Divergence and Risk for Binary Experiments
The Journal of Machine Learning Research
On a non-monotonicity effect of similarity measures
SIMBAD'11 Proceedings of the First international conference on Similarity-based pattern recognition
| Hi-index | 755.08 |
The paper deals with the f-divergences of Csiszar generalizing the discrimination information of Kullback, the total variation distance, the Hellinger divergence, and the Pearson divergence. All basic properties of f-divergences including relations to the decision errors are proved in a new manner replacing the classical Jensen inequality by a new generalized Taylor expansion of convex functions. Some new properties are proved too, e.g., relations to the statistical sufficiency and deficiency. The generalized Taylor expansion also shows very easily that all f-divergences are average statistical informations (differences between prior and posterior Bayes errors) mutually differing only in the weights imposed on various prior distributions. The statistical information introduced by De Groot and the classical information of Shannon are shown to be extremal cases corresponding to alpha=0 and alpha=1 in the class of the so-called Arimoto alpha-informations introduced in this paper for 0