Conference PaperNeural Network-based Estimation of the MMSEDiaz, Mario; Kairouz, Peter; Liao, Jiachun; Sankar, LalithanullThe minimum mean-square error (MMSE) achievable by optimal estimation of a random variable S given another random variable T is of much interest in a variety of statistical contexts. Motivated by a growing interest in auditing machine learning models for unintended information leakage, we propose a neural network-based estimator of this MMSE. We derive a lower bound for the MMSE based on the proposed estimator and the Barron constant associated with the conditional expectation of S given T . Since the latter is typically unknown in practice, we derive a general bound for the Barron constant that produces order optimal estimates for canonical distribution models.2021-10-0110297195International Symposium on Information Theory1023 to 1028https://doi.org/10.1109/ISIT45174.2021.95180631815361; 2031799; 1901243; 2007688National Science Foundation