Sanjay Shakkottai
Professor
Department of Electrical and Computer Engineering
The University of Texas at Austin
Topic
Notes
00 - Overview
01 - Probability review
02 - Concentrations review
03 - Framework and regret
04 - ETC Algorithm
05 - UCB fixed-horizon
06 - UCB Infinite Horizon
07 - KL UCB
08 - EXP3 Algorithm
09 - Lower bound ideas
10 - Bretagnolle-Huber Inequality
11 - Minimax Lower Bounds
12 - Instance dependent lower bound
13 - Bandits with Oblivious Experts
14 - Contextual Bandits
14a - Tutorial on Least Squares Regression
15 - LinUCB Regret Analysis
16 - Kiefer-Wolfowitz Theorem
17 - Linear Bandits with Finitely Many Arms
18 - Adversarial Linear BanditsÂ
19 - Review of Bregman Divergence
20 - Online Linear Optimization
21 - Online Classification-Part-1
22 - Online Classification-Part-2
23 - Pure Exploration
24 - Bayesian Bandits
25 - Thompson SamplingÂ