Overview
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.
Syllabus
Introduction
Challenges in Machine Learning
Problem Statement
Problem Variants
Collaborative Learning Model
Communication Step
Speedup
Tradeoffs between runs and speedup
Results
Summary
Technical Details
NonAdaptive Setting
Hardings Prescription
Pyramid Like Distribution
Technical Challenges
New Ideas
Input Class
Adaptive Case
Other Results
Paper Summary
Taught by
IEEE FOCS: Foundations of Computer Science