18 citations · 24 across the 11 of their papers we have counts for
11 papers
Bandits in Flux: Adversarial Constraints in Dynamic Environments
Tareq Si Salem
We investigate the challenging problem of adversarial multi-armed bandits operating under time-varying constraints, a scenario motivated by numerous real-world applications. To add…
KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
Dmitry Akulov, Mohamed Sana, Antonio De Domenico +3
Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a…
A Multi-Armed Bandit Framework for Online Optimisation in Green Integrated Terrestrial and Non-Terrestrial Networks
Henri Alam, Antonio de Domenico, Tareq Si Salem +1
Integrated terrestrial and non-terrestrial network (TN-NTN) architectures offer a promising solution for expanding coverage and improving capacity for the network. While non-terres…
Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing
Andrei-Laurentiu Bornea, Fadhel Ayed, Antonio De Domenico +3
Artificial intelligence will be one of the key pillars of the next generation of mobile networks (6G), as it is expected to provide novel added-value services and improve network p…
Goal-Oriented Time-Series Forecasting: Foundation Framework Design
Luca-Andrei Fechete, Mohamed Sana, Fadhel Ayed +4
Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downs…
Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networks
Caelin Kaplan, Angelo Rodio, Tareq Si Salem +2
As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational…
Online Submodular Maximization via Online Convex Optimization
Tareq Si Salem, Gözde Özcan, Iasonas Nikolaou +2
We study monotone submodular maximization under general matroid constraints in the online setting. We prove that online optimization of a large class of submodular functions, namel…
Enabling Long-term Fairness in Dynamic Resource Allocation
T. Si-Salem, G. Iosifidis, G. Neglia
We study the fairness of dynamic resource allocation problem under the -fairness criterion. We recognize two different fairness objectives that naturally arise in this problem:…
Ascent Similarity Caching with Approximate Indexes
T. Si-Salem, G. Neglia, D. Carra
Similarity search is a key operation in multimedia retrieval systems and recommender systems, and it will play an important role also for future machine learning and augmented real…
Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees
T. Si Salem, G. Castellano, G. Neglia +2
An increasing number of applications rely on complex inference tasks that are based on machine learning (ML). Currently, there are two options to run such tasks: either they are se…
No-Regret Caching via Online Mirror Descent
T. Si Salem, G. Neglia, S. Ioannidis
We study an online caching problem in which requests can be served by a local cache to avoid retrieval costs from a remote server. The cache can update its state after a batch of r…