Learning-Theoretic Foundations of Algorithm Design

Overview

Discover insights into AI applications for mathematics and theoretical computer science in this talk by Maria-Florina Balcan from Carnegie Mellon University.

Syllabus

• Introduction to Learning Theory
Overview of Machine Learning Concepts
The Role of Learning Theory in AI
• Fundamental Models of Learning
Probably Approximately Correct (PAC) Learning
Online Learning
Statistical Learning Frameworks
• Algorithm Design and Analysis
Basics of Efficient Algorithm Design
Approximation Algorithms
Randomized Algorithms
• Connections Between Learning Theory and Algorithm Design
Leveraging Learning for Algorithm Design
Learning Algorithms in Theoretical Computer Science
• Theoretical Insights into AI Applications
Applications in Mathematics
Applications in Theoretical Computer Science
• Case Studies and Real-World Applications
Case Studies from Carnegie Mellon Research
Breakthroughs in AI with Theoretical Underpinnings
• Advanced Topics in Learning-Theoretic Techniques
Game-Theoretic Learning
Multi-Armed Bandits and Exploration vs. Exploitation
• Future Directions and Open Problems
Challenges in Learning-Theoretic Algorithm Design
Emerging Research Directions in AI
• Conclusion and Summary
Recap of Key Concepts
Final Thoughts on Learning-Theoretic Foundations
• Supplemental Readings and Resources
Recommended Texts and Papers
Online Resources and Lectures
• Evaluation and Assessment
Problem Sets
Projects and Presentations
Final Examination

Subjects

Computer Science