3 papers
stat.ML2025
Lower Bounds on the MMSE of Adversarially Inferring Sensitive Features
Monica Welfert, Nathan Stromberg, Mario Diaz +1
We propose an adversarial evaluation framework for sensitive feature inference based on minimum mean-squared error (MMSE) estimation with a finite sample size and linear predictive…
math.PR2024
Non-commutative Stein's Method: Applications to Free Probability and Sums of Non-commutative Variables
Mario Díaz, Arturo Jaramillo
We present a straightforward formulation of Stein's method for the semicircular distribution, specifically designed for the analysis of non-commutative random variables. Our approa…
cs.LG2023
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses
Shahab Asoodeh, Mario Diaz
The Noisy-SGD algorithm is widely used for privately training machine learning models. Traditional privacy analyses of this algorithm assume that the internal state is publicly rev…