Optimal exponential bounds for aggregation of density estimators (Q502865)

The paper studies the problem of estimating an unknown density function based on observations. It shows that two classical estimators, the exponential weights aggregate and the empirical risk minimization are suboptimal in deviation. It then defines a penalized procedure based on which a sharp oracle inequality in deviation is derived, which achieves an optimal rate in deviation. Finally, the paper provides a lower bound that shows that neither the achieved rate nor the deviation term can be further improved.