Machine Learning for Algorithm Design

Explore the intersection of machine learning and algorithm design in this 58-minute ACM conference talk. Delve into the limitations of traditional worst-case analysis and discover how data-driven approaches can enhance algorithmic performance. Learn about recent advancements that provide theoretical foundations for data-driven algorithm design, including specific case studies and broadly applicable principles for combinatorial problems. Gain insights from Maria Florina Balcan, a distinguished computer scientist, as she discusses topics such as clustering, learning theory, and online learning formalization. Understand the potential of machine learning to revolutionize algorithm design and its applications across various domains.

Introduction
Overview
Clustering
Machine Learning
Learning Theory
DataDriven Algorithm Design
Other Applications
Online Learning Formalization
Summary
Conclusion