Learn · Bandit Algorithm (Online Machine Learning)
Lecture 32 of 59Week 7
Lecture 32 : Optimism in the Face of Uncertainty
Prof. Manjesh Hanawal · IIT Bombay
Credits and licence
- From
- Bandit Algorithm (Online Machine Learning), IIT Bombay (at NPTEL)
- Licence
- CC BY-NC-SA, as NPTEL states it. Non-commercial use only.
- Attribution
- NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
- Who can watch
- Tweens profiles and older. How courses are placed
All the lectures
- Lecture 1 : Introduction to Online Learning –I
- Lecture 2 : Introduction to Online Learning –II
- Lecture 3 : Basics of Statistical Learning
- Lecture 4 : Empirical risk minimization
- Lecture 5 : Consistency Halving algorithm
- Lecture 6 : Online Learnability
- Lecture 7 : Standard Optimal Algorithm
- Lecture 8 : Classification in unrealizability case
- Lecture 9 : Covers Impossibility Result
- Lecture 10 : Weighted Majority
- Lecture 11 : Proof Weighted Majority
- Lecture 12 : Full Information vs Bandit Setting
- Lecture 13 : Adversarial Bandit Setting
- Lecture 14 : Exponential Weights for Exploration and Exploitation Algorithm
- Lecture 15 : Regret Bound of Exp3
- Lecture 16 : Regret Bound of Exp3(Contd.)
- Lecture 17 : Exp3.P and Exp3.IX
- Lecture 18 : Online Convex Optimisation
- Lecture 19 : Follow the Leader (FTL) Algorithm
- Lecture 20 : Follow the Regularized Leader
- Lecture 21 : Online Gradient Descent
- Lecture 22 : Strongly Convex Function
- Lecture 23 : FoReL with Strongly Convex Regulariser
- Lecture 24 : FoReL with Strongly Convex Regulariser (Contd.)
- Lecture 25 : Euclidean and Entropy Regularizer
- Lecture 26 : Introduction to Stochastic Bandits
- Lecture 27 : Concentration Inequalities
- Lecture 28 : Subgaussian Random Variable
- Lecture 29 : Regret Definition and Regret Decomposition
- Lecture 30 : Explore and Commit (ETC) Algorithm
- Lecture 31 : Regret Analysis and ETC
- Lecture 32 : Optimism in the Face of Uncertainty
- Lecture 33 : Upper Confidence Bound Algorithm
- Lecture 34 : Regret Analysis of UCB
- Lecture 35 : Problem Dependent and Independent Bounds of UCB
- Lecture 36 : KL-UCB Algorithm
- Lecture 37 : Thompson Sampling - Brief Discussion
- Lecture 38 : Proof Idea of Lower Bounds - 1
- Lecture 39 : Proof Idea of Lower Bounds - 2
- Lecture 40 : Proof of Lower Bound-1
- Lecture 41 : Proof of Lower Bound-2
- Lecture 42 : Stochastic Contextual Bandits
- Lecture 43 : Introduction to Stochastic Linear Bandits
- Lecture 44 : Stochastic Linear Bandits
- Lecture 45 : Regret Analysis of SLB-I
- Lecture 46 : Regret Analysis of SLB - II
- Lecture 47 : Regret Analysis of SLB-III
- Lecture 48 : Construction of Confidence Ellipsoid - I
- Lecture 49 : Construction of Confidence Ellipsoids - II
- Lecture 50 : Adversarial Contextual Bandits - I
- Lecture 51 : Adversarial Contextual Bandits II
- Lecture 52 : Exp4 Algorithm
- Lecture 53 : Regret of Exp4
- Lecture 54 : Adversarial Linear Bandits
- Lecture 55 : Exp3 for Adversarial Linear Bandits
- Lecture 56 : Introduction to Pure Exploration and its lower bounds
- Lecture 57 : Uniform Exploration
- Lecture 58 : KL-LUCB
- Lecture 59 : Lil’ UCB