76 citations · 85 across the 7 of their papers we have counts for
7 papers
Arbitrariness Lies Beyond the Fairness-Accuracy Frontier
Carol Xuan Long, Hsiang Hsu, Wael Alghamdi +1
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predicti…
The Saddle-Point Accountant for Differential Privacy
Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon +4
We introduce a new differential privacy (DP) accountant called the saddle-point accountant (SPA). SPA approximates privacy guarantees for the composition of DP mechanisms in an acc…
Cactus Mechanisms: Optimal Differential Privacy Mechanisms in the Large-Composition Regime
Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon +3
Most differential privacy mechanisms are applied (i.e., composed) numerous times on sensitive data. We study the design of optimal differential privacy mechanisms in the limit of a…
Beyond Adult and COMPAS: Fairness in Multi-Class Prediction
Wael Alghamdi, Hsiang Hsu, Haewon Jeong +4
We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks. We formulate this problem in terms of "projecting" a pre-trained (and pote…
Measuring Information from Moments
Wael Alghamdi, Flavio P. Calmon
We investigate the problem of representing information measures in terms of the moments of the underlying random variables. First, we derive polynomial approximations of the condit…
Polynomial Approximations of Conditional Expectations in Scalar Gaussian Channels
Wael Alghamdi, Flavio P. Calmon
We consider a channel where is a random variable satisfying and is an independent standard normal random variable. We show that the minimum…
Optimal Spectral Initialization for Signal Recovery with Applications to Phase Retrieval
Wangyu Luo, Wael Alghamdi, Yue M. Lu
We present the optimal design of a spectral method widely used to initialize nonconvex optimization algorithms for solving phase retrieval and other signal recovery problems. Our w…