69 citations · 88 across the 15 of their papers we have counts for
17 papers
On a divergence-based prior analysis of stick-breaking processes
José A. Perusquía, Mario Diaz, Ramsés H. Mena
The nonparametric view of Bayesian inference has transformed statistics and many of its applications. The canonical Dirichlet process and other more general families of nonparametr…
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…
Lower Bounds for the MMSE via Neural Network Estimation and Their Applications to Privacy
Mario Diaz, Peter Kairouz, Lalitha Sankar
The minimum mean-square error (MMSE) achievable by optimal estimation of a random variable given another random variable is of much interest i…
Contraction of -Divergence and Its Applications to Privacy
Shahab Asoodeh, Mario Diaz, Flavio P. Calmon
We investigate the contraction coefficients derived from strong data processing inequalities for the -divergence. By generalizing the celebrated Dobrushin's coefficient from t…
On the alpha-loss Landscape in the Logistic Model
Tyler Sypherd, Mario Diaz, Lalitha Sankar +1
We analyze the optimization landscape of a recently introduced tunable class of loss functions called -loss, , in the logistic model. This family encapsulates t…
To Split or Not to Split: The Impact of Disparate Treatment in Classification
Hao Wang, Hsiang Hsu, Mario Diaz +1
Disparate treatment occurs when a machine learning model yields different decisions for individuals based on a sensitive attribute (e.g., age, sex). In domains where prediction acc…
Privacy Amplification of Iterative Algorithms via Contraction Coefficients
Shahab Asoodeh, Mario Diaz, Flavio P. Calmon
We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens. We demonstrate that differential privac…
Theoretical Guarantees for Model Auditing with Finite Adversaries
Mario Diaz, Peter Kairouz, Jiachun Liao +1
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees…
A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization
Tyler Sypherd, Mario Diaz, John Kevin Cava +3
We introduce a tunable loss function called -loss, parameterized by , which interpolates between the exponential loss (), the log-loss (), and the…
A Tunable Loss Function for Binary Classification
Tyler Sypherd, Mario Diaz, Lalitha Sankar +1
We present -loss, , a tunable loss function for binary classification that bridges log-loss () and - loss (). We prove that -loss has a…
On the Robustness of Information-Theoretic Privacy Measures and Mechanisms
Mario Diaz, Hao Wang, Flavio P. Calmon +1
Consider a data publishing setting for a dataset composed by both private and non-private features. The publisher uses an empirical distribution, estimated from i.i.d. samples,…
On the Contractivity of Privacy Mechanisms
Mario Diaz, Lalitha Sankar, Peter Kairouz
We present a novel way to compare the statistical cost of privacy mechanisms using their Dobrushin coefficient. Specifically, we provide upper and lower bounds for the Dobrushin co…
On the Noise-Information Separation of a Private Principal Component Analysis Scheme
Mario Diaz, Shahab Asoodeh, Fady Alajaji +3
In a survey disclosure model, we consider an additive noise privacy mechanism and study the trade-off between privacy guarantees and statistical utility. Privacy is approached from…
The Utility Cost of Robust Privacy Guarantees
Hao Wang, Mario Diaz, Flavio P. Calmon +1
Consider a data publishing setting for a data set with public and private features. The objective of the publisher is to maximize the amount of information about the public feature…
Estimation Efficiency Under Privacy Constraints
Shahab Asoodeh, Mario Diaz, Fady Alajaji +1
We investigate the problem of estimating a random variable under a privacy constraint dictated by another random variable , where estimation ef…
Privacy-Aware Guessing Efficiency
Shahab Asoodeh, Mario Diaz, Fady Alajaji +1
We investigate the problem of guessing a discrete random variable under a privacy constraint dictated by another correlated discrete random variable , where both guessing ef…
Information Extraction Under Privacy Constraints
Shahab Asoodeh, Mario Diaz, Fady Alajaji +1
A privacy-constrained information extraction problem is considered where for a pair of correlated discrete random variables governed by a given joint distribution, an agent…