Khaled Mazen Mahmoud Elsayed Eldowa

Dottorato in Intelligenza Artificiale , 37^o ciclo (2021-2024)

Dottorato concluso nel 2025

Leveraging Structured Feedback in Online Learning

Nicolo' Antonio Cesa-bianchiMarcello Restelli

Eldowa, Khaled; Paudice, Andrea (2024)
General Tail Bounds for Non-Smooth Stochastic Mirror Descent. In: The International Conference on Artificial Intelligence and Statistics, Valencia (ESP), 2-4 May 2024, pp. 3205-3213. ISSN 2640-3498
Contributo in Atti di Convegno (Proceeding)
Eldowa, Khaled; Cesa-Bianchi, Nicolò; Maria Metelli, Alberto; Restelli, Marcello (2024)
Information Capacity Regret Bounds for Bandits with Mediator Feedback. In: JOURNAL OF MACHINE LEARNING RESEARCH, vol. 25, pp. 1-36. ISSN 1533-7928
Contributo su Rivista
Eldowa, Khaled; Esposito, Emmanuel; Cesari, Tom; Cesa-Bianchi, Nicolò (2023)
On the Minimax Regret for Online Learning with Feedback Graphs. In: NeurIPS 2023, the Thirty-seventh Annual Conference on Neural Information Processing Systems, New Orleans (USA), Dec 10 through Dec 16, 2023, pp. 46122-46133. ISSN 1049-5258
Contributo in Atti di Convegno (Proceeding)
Eldowa, Khaled; Bisi, Lorenzo; Restelli, Marcello (2022)
Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning. In: The 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022), pp. 10028-10066
Contributo in Atti di Convegno (Proceeding)