PAC Mode Estimation Using PPR Martingale Confidence Sequences
Centre for Networked Intelligence, IISc via YouTube
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Free courses from frontend to fullstack and AI
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Watch a technical lecture exploring the application of prior-posterior-ratio (PPR) martingale confidence sequences to mode estimation in discrete distributions. Learn how the "one-versus-one" principle proves more efficient than "one-versus-rest" when generalizing from binary to multi-class problems, and discover the PPR-1v1 stopping rule's asymptotic optimality and practical advantages. Examine real-world applications in election forecasting and blockchain smart contract verification through demonstrations by Prof. Shivaram Kalyanakrishnan, an Associate Professor at IIT Bombay known for his contributions to artificial intelligence, machine learning, and robotics research.
Syllabus
PAC Mode Estimation using PPR Martingale Confidence Sequences | Prof. Shivaram Kalyanakrishnan
Taught by
Centre for Networked Intelligence, IISc