2016/03/28 by Shashank Kumar Singh, Singh, Shashank, Barnabás Póczos +1 · 1 citation
Computer Science · Engineering · Mathematics · #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Machine Learning (stat.ML) #Sparse and Compressive Sensing Techniques #Statistical Methods and Inference #Statistics Theory (math.ST)
paper · pdf · doi:10.48550/arxiv.1603.08589
openalex publication_date 2016/03/28 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/28
Estimating divergences in a consistent way is of great importance in many\nmachine learning tasks. Although this is a fundamental problem in nonparametric\nstatistics, to the best of our knowledge there has been no finite sample\nexponential inequality convergence bound derived for any divergence estimators.\nThe main contribution of our work is to provide such a bound for an estimator\nof R 'enyi-\α divergence for a smooth H "older class of densities on the\nd-dimensional unit cube [0, 1]d. We also illustrate our theoretical\nresults with a numerical experiment.\n