All Dates/Times are Australian Eastern Standard Time (AEST)

Technical Program

Paper Detail

Paper IDD3-S1-T3.1
Paper Title Neural Network-based Estimation of the MMSE
Authors Mario Diaz, Universidad Nacional Autónoma de México, Mexico; Peter Kairouz, Google AI, United States; Jiachun Liao, Lalitha Sankar, Arizona State University, United States
Session D3-S1-T3: Neural Estimation
Chaired Session: Wednesday, 14 July, 22:00 - 22:20
Engagement Session: Wednesday, 14 July, 22:20 - 22:40
Abstract The 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.