Workshop Schedule
Assembly 8:30 - 9:00
8:55 - 9:00
Ana Bušić.
9:00 - 10:00
Speaker 1, 9:00-9:30: Srinivas Shakkottai. "Compressive Sensing for Zeroth-Order Gradient Estimation in Online Convex Optimization"
Speaker 2, 9:30-10:00: Attila Eryilmaz. "Recurrent Natural Policy Gradient for POMDPs"
Coffee Break 10:00 - 10:15
10:15 - 10:45
Speaker 3, 10:15-10:45: Gauri Joshi. "Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems"
10:45 - 11:10
(1-2 Slides, 4 Minutes per Poster, 25 minutes total)
Presenter 1, 10:45-10:49: Thomas Le Core.
Presenter 2, 10:49-10:53: Panagiotis Charatsaris.
Presenter 3, 10:53-10:57: Giorgos Kallitsis.
Presenter 4, 10:57-11:01: Anastasios Zafeiropoulos.
Presenter 5, 11:01-11:05: Grigoris Kakkavas.
Presenter 6, 11:05-11:09: Georgia Stavropoulou.
11:10 - 12:00
Poster 1: Thomas Le Core. "Moment Constrained Optimal Transport for Control Applications"
Poster 2: Panagiotis Charatsaris. "Distributed Resource Allocation in Wireless Federated Learning Networks: The Perspective of Satisfaction Equilibrium"
Poster 3: Giorgos Kallitsis. "On Optimal Decision-Making in Wireless Energy-Harvesting Networks with Age-of-Information Features"
Poster 4: Anastasios Zafeiropoulos. "A Multi-Agent RL-Driven Approach to Guide Autoscaling of Distributed Applications in the Computing Continuum"
Poster 5: Grigoris Kakkavas. "AI-Driven Management and Orchestration of 6G-Enabled Services Across the Computing Continuum"
Poster 6: Georgia Stavropoulou. "An Iterative Convexification Approach for Congestion Planning in Uncertain Multi-Hop Network Settings"
Lunch Break 12:00 - 13:00
13:00 - 15:00
Speaker 4, 13:00-13:30: Jian Li. "Direct Online Preference Learning for Restless Multi-Armed Bandits with Preference Feedback"
Speaker 5, 13:30-14:00: Rahul Vaze. "Optimal Bounds for Constrained Online Convex Optimization"
Speaker 6, 14:00-14:30: XYZ. "Online Learning for Control"
Speaker 7, 14:30-15:00: Krishna Jagannathan. "Classical Bandit Algorithms for Entanglement Detection in Parameterized Qubit States"
Coffee Break 15:00 - 15:15
15:15 - 17:15
Speaker 8, 15:15-15:45: Sushil Varma. "Electric Vehicle Fleet Sizing and Charging Infrastructure Planning"
Speaker 9, 15:45-16:15: I-Hong Hou. "Deep RL for Index Policy in Restless Bandit Problems"
Speaker 10, 16:15-16:45: Jia (Kevin) Liu. "Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning"
Speaker 11, 16:45-17:15: Ana Bušić. "Kullback–Leibler Quadratic Cooperative Mean-Field Control"
17:15 - 17:20
Ana Bušić.