Local continuity of log-concave projection, with applications to estimation under model misspecification (Q1983616)

The log-concave projection is an operator that maps a \(d\)-dimensional distribution \textbf{P} to an approximating log-concave density. With suitable metrics on the underlying spaces, the projection is continuous but not uniformly continuous. In this paper, the authors prove a local uniform continuity result for log-concave projection -- in particular, establishing that this map is locally Hölder-(1/4) continuous. A matching lower bound verifies that the exponent cannot be improved. This paper also examines the implications of this continuity result for the empirical setting -- given a sample drawn from a distribution \textbf{P}, and bounds the squared Hellinger distance between the log-concave projection of the empirical distribution of the sample, and the log-concave projection of \textbf{P}.