5 papers · 1 filter
Certifiably Interpretable Training of ReLU-MLPs for Boolean Tasks with Guaranteed Truth-Table Generalization
Hrad Ghoukasian, Anastasis Kratsios
As compute scales, models evolve, and training algorithms advance, our ability to explain the increasingly powerful AI systems they enable is eroding. To help safeguard interpretab…
A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning
Minghui Chen, Hrad Ghoukasian, Ruinan Jin +3
Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data…
Optimal Fairness under Local Differential Privacy
Hrad Ghoukasian, Shahab Asoodeh
We investigate how to optimally design local differential privacy (LDP) mechanisms that reduce data unfairness and thereby improve fairness in downstream classification. We first d…
Locally Optimal Private Sampling: Beyond the Global Minimax
Hrad Ghoukasian, Bonwoo Lee, Shahab Asoodeh
We study the problem of sampling from a distribution under local differential privacy (LDP). Given a private distribution , the goal is to generate a single samp…
Differentially Private Fair Binary Classifications
Hrad Ghoukasian, Shahab Asoodeh
In this work, we investigate binary classification under the constraints of both differential privacy and fairness. We first propose an algorithm based on the decoupling technique…