Empirical entropy, minimax regret and minimax risk
Authors:
- Alexander RakhlinARAlexander Rakhlin
- Karthik SridharanKSKarthik Sridharan
- Alexandre B. TsybakovATAlexandre B. Tsybakov
- 1 May 2017
- journal article
- research article
- Published by Bernoulli Society for Mathematical Statistics and Probability in Bernoulli
- Vol. 23 (2) , 789-824
Abstract
Project Euclid - mathematics and statistics onlineKeywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Sparse Estimation by Exponential WeightingStatistical Science, 2012
- Learning by mirror averagingThe Annals of Statistics, 2008
- Generalized mirror averaging and D-convex aggregationMathematical Methods of Statistics, 2007
- Aggregating regression procedures to improve performanceBernoulli, 2004
- Rademacher penalties and structural risk minimizationIEEE Transactions on Information Theory, 2001
- Adaptive model selection using empirical complexitiesThe Annals of Statistics, 1999
- Uniform and universal Glivenko-Cantelli classesJournal of Theoretical Probability, 1991
- Estimating a Regression FunctionThe Annals of Statistics, 1990
- Central Limit Theorems for Empirical MeasuresThe Annals of Probability, 1978
- Convergence of Estimates Under Dimensionality RestrictionsThe Annals of Statistics, 1973