3 papers
cs.IT2026
On the Information Bottleneck for Stable Variables
Dongmin Park, Jihad Fahs, Mohamad Assaad
We consider a generalization of the Gaussian information bottleneck problem to jointly stable variables and . Specifically, for , where is stable and independ…
cs.CR2026
Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels
Anthony Ayli, Khalil Harris, Jihad Fahs +1
Homomorphic encryption (HE) enables privacy-preserving aggregation in federated learning (FL) by allowing the server to operate on encrypted data without decryption. Existing HE-ov…
cs.LG2025
Energy-Efficient Quantized Federated Learning for Resource-constrained IoT devices
Wilfrid Sougrinoma Compaoré, Yaya Etiabi, El Mehdi Amhoud +1
Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative machine learning while preserving data privacy, making it particularly suitable for Internet…