activity
20242026
collaborators

8 papers

cs.AR2026

Event-triggered Implicit Perturbation for Zeroth-Order Fine-Tuning of Spiking Transformers

Tengteng Lei, Prabodh Katti, Rashi Dutt +5

Zeroth-order (ZO) optimization estimates gradients using only forward-pass evaluations, making it suitable for fine-tuning non-differentiable, event-driven spiking neural networks…

cs.LG2026

Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects

Ayed M. Alrashdi, Oussama Dhifallah, Houssem Sifaou

Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is ident…

eess.SP2026

How to Bridge the Sim-to-Real Gap in Digital Twin-Aided Telecommunication Networks

Clement Ruah, Houssem Sifaou, Osvaldo Simeone +1

Training effective artificial intelligence models for telecommunications is challenging due to the scarcity of deployment-specific data. Real data collection is expensive, and avai…

cs.LG2026

Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration

Seonghoon Yoo, Houssem Sifaou, Sangwoo Park +2

Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable position estimates. One remedy is to…

cs.LG2025

Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization

Houssem Sifaou, Osvaldo Simeone

Optimizing a reinforcement learning (RL) policy typically requires extensive interactions with a high-fidelity simulator of the environment, which are often costly or impractical.…

eess.SP2025

Context-Aware Doubly-Robust Semi-Supervised Learning

Clement Ruah, Houssem Sifaou, Osvaldo Simeone +1

The widespread adoption of artificial intelligence (AI) in next-generation communication systems is challenged by the heterogeneity of traffic and network conditions, which call fo…