Collaborative Learning with Limited Interaction - Tight Bounds for Distributed Exploration in Bandits

This course focuses on collaborative learning with limited interaction, specifically exploring tight bounds for distributed exploration in bandits. The learning outcomes include understanding the challenges in machine learning, exploring different problem variants, and grasping the collaborative learning model. The course teaches skills such as communication steps, speedup techniques, and analyzing tradeoffs between runs and speedup. The teaching method involves presenting technical details, discussing an adaptive setting, and summarizing research results. The intended audience for this course is individuals interested in distributed exploration in machine learning and collaborative learning techniques.