Chasing convex bodies and other random topics with Dr. Sébastien Bubeck

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=7O7qzgYbXEA


Duration: 35:50
1,430 views
32

Episode 53 | December 5, 2018

Dr. Sébastien Bubeck explains the difficulty of the multi-armed bandit problem in the context of a parameter- and data-rich online world. He also discusses a host of topics from randomness and convex optimization to metrical task systems and log n competitiveness to the surprising connection between Gaussian kernels and what he calls some of the most beautiful objects in mathematics.



Other Videos By Microsoft Research


2019-02-06EmpowerMD: Medical conversations to medical intelligence
2019-01-30Advances in AI and the Future of Work: Perspectives and Discussion
2019-01-23Empowering people with AI with Dr. Cecily Morrison
2019-01-17Building contextually intelligent assistants with Dr. Paul Bennett
2019-01-14The Microsoft Research intern experience with Robyn McMillan
2019-01-14The Microsoft Research intern experience with David George Robertson
2019-01-09Scaling the Everest of software security with Dr. Jonathan Protzenko
2019-01-07Canetroller: Navigating virtual reality with haptic and auditory cane stimulation
2019-01-02Social and Emotional Artificial Intelligence
2018-12-13Soundscaping the world with Amos Miller
2018-12-13Chasing convex bodies and other random topics with Dr. Sébastien Bubeck
2018-12-06Automated Reasoning of Database Queries
2018-12-06How to Obtain and Run Light and Efficient Deep Learning Networks
2018-12-06Machine Teaching Demo
2018-12-06Advanced Machine Learning Day 3: Neural Program Synthesis
2018-12-06Advanced Machine Learning Day 3: Neural Architecture Search
2018-12-06Delayed Impact of Fair Machine Learning
2018-12-03Machine learning and the learning machine with Dr. Christopher Bishop
2018-12-03Deep Generative Models for Imitation Learning and Fairness
2018-11-29Machine Teaching Overview
2018-11-28Policy Optimization as Predictable Online Learning Problems: Imitation Learning and Beyond


Tags:
microsoft research
microsoft podcast