7 papers
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 Closed-Form Formula for Consistent Lipschitz Regression on Metric Spaces with Sparse Neural Network Realizations
Ruiyang Hong, Hrad Ghoukasian, Anastasis Kratsios
Several classical machine-learning methods, such as KRRs and SVRs, are both computationally and analytically tractable since their estimators either admit closed-form expressions o…
Certifiable Boolean Reasoning Is Universal
Wenhao Li, Anastasis Kratsios, Hrad Ghoukasian +1
The proliferation of agentic systems has thrust the reasoning capabilities of AI into the forefront of contemporary machine learning. While it is known that there \emph{exist} neur…
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…