Even though the statistical theory of linear inverse problems is a well-studied topic, certain relevant cases remain open. Among these is the estimation of functions of bounded variation (), meaning functions on a -dimensional domain whose weak first derivatives are finite Radon measures. The estimation of functions is relevant in many applications, since it involves minimal smoothness assumptions and gives simplified, interpretable cartoonized reconstructions. In this paper we propose a novel technique for estimating functions in an inverse problem setting, and provide theoretical guaranties by showing that the proposed estimator is minimax optimal up to logarithms with respect to the -risk, for any . This is to the best of our knowledge the first convergence result for functions in inverse problems in dimension , and it extends the results by Donoho (Appl. Comput. Harmon. Anal., 2(2):101--126, 1995) in . Furthermore, our analysis unravels a novel regime for large in which the minimax rate is slower than , where is the degree of ill-posedness: our analysis shows that this slower rate arises from the low smoothness of functions. The proposed estimator combines variational regularization techniques with the wavelet-vaguelette decomposition of operators.
View on arXiv