Modules / Lectures
Module NameDownload
noc20_mg37_assignment_Week_1noc20_mg37_assignment_Week_1
noc20_mg37_assignment_Week_10noc20_mg37_assignment_Week_10
noc20_mg37_assignment_Week_11noc20_mg37_assignment_Week_11
noc20_mg37_assignment_Week_12noc20_mg37_assignment_Week_12
noc20_mg37_assignment_Week_2noc20_mg37_assignment_Week_2
noc20_mg37_assignment_Week_3noc20_mg37_assignment_Week_3
noc20_mg37_assignment_Week_4noc20_mg37_assignment_Week_4
noc20_mg37_assignment_Week_5noc20_mg37_assignment_Week_5
noc20_mg37_assignment_Week_6noc20_mg37_assignment_Week_6
noc20_mg37_assignment_Week_7noc20_mg37_assignment_Week_7
noc20_mg37_assignment_Week_8noc20_mg37_assignment_Week_8
noc20_mg37_assignment_Week_9noc20_mg37_assignment_Week_9


Sl.No Chapter Name MP4 Download
1Lecture 1: Introduction to Online Learning –IDownload
2Lecture 2: Introduction to Online Learning –IDownload
3Lecture 3: Basics of Statistical LearningDownload
4Lecture 4: Empirical risk minimization Download
5Lecture 5: Consistency Halving algorithm Download
6Lecture 6: Online Learnability Download
7Lecture 7: Standard Optimal Algorithm Download
8Lecture 8: Classification in unrealizability caseDownload
9Lecture 9: Covers Impossibility ResultDownload
10Lecture 10: Weighted Majority Download
11Lecture 11: Proof Weighted MajorityDownload
12Lecture 12: Full Information vs Bandit SettingDownload
13Lecture 13: Adversarial Bandit SettingDownload
14Lecture 14: Exponential Weights for Exploration and Exploitation AlgorithmDownload
15Lecture 15: Regret Bound of Exp3Download
16Lecture 16: Regret Bound of Exp3(Contd.)Download
17Lecture 17: Exp3.P and Exp3.IXDownload
18Lecture 18: Online Convex OptimisationDownload
19Lecture 19: Follow the Leader (FTL) AlgorithmDownload
20Lecture 20: Follow the Regularized LeaderDownload
21Lecture 21: Online Gradient DescentDownload
22Lecture 22: Strongly Convex FunctionDownload
23Lecture 23: FoReL with Strongly Convex RegulariserDownload
24Lecture 24: FoReL with Strongly Convex Regulariser (Contd.)Download
25Lecture 25: Euclidean and Entropy RegularizerDownload
26Lecture 26: Introduction to Stochastic BanditsDownload
27Lecture 27: Concentration InequalitiesDownload
28Lecture 28: Subgaussian Random VariableDownload
29Lecture 29: Regret Definition and Regret DecompositionDownload
30Lecture 30: Explore and Commit (ETC) AlgorithmDownload
31Lecture 31: Regret Analysis and ETCDownload
32Lecture 32: Optimism in the Face of UncertaintyDownload
33Lecture 33: Upper Confidence Bound AlgorithmDownload
34Lecture 34 : Regret Analysis of UCB Download
35Lecture 35 : Problem Dependent and Independent Bounds of UCB Download
36Lecture 36 : KL-UCB AlgorithmDownload
37Lecture 37 : Thompson Sampling - Brief DiscussionDownload
38Lecture 38 : Proof Idea of Lower Bounds - 1Download
39Lecture 39 : Proof Idea of Lower Bounds - 2 Download
40Lecture 40 : Proof of Lower Bound-1Download
41Lecture 41 : Proof of Lower Bound-2Download
42Lecture 42 : Stochastic Contextual Bandits Download
43Lecture 43 : Introduction to Stochastic Linear BanditsDownload
44Lecture 44 : Stochastic Linear BanditsDownload
45Lecture 45 : Regret Analysis of SLB-I Download
46Lecture 46 : Regret Analysis of SLB - II Download
47Lecture 47 : Regret Analysis of SLB-III Download
48Lecture 48 : Construction of Confidence Ellipsoid - IDownload
49Lecture 49 : Construction of Confidence Ellipsoids - IIDownload
50Lecture 50 : Adversarial Contextual Bandits - IDownload
51Lecture 51 : Adversarial Contextual Bandits IIDownload
52Lecture 52 : Exp4 AlgorithmDownload
53Lecture 53 : Regret of Exp4Download
54Lecture 54 : Adversarial Linear BanditsDownload
55Lecture 55 : Exp3 for Adversarial Linear BanditsDownload
56Lecture 56 : Introduction to Pure Exploration and its lower boundsDownload
57Lecture 57 : Uniform ExplorationDownload
58Lecture 58 : KL-LUCBDownload
59Lecture 59 : Lil’ UCBDownload
60Lecture 60 : Lower Bound for Pure Exploration ProblemDownload

Sl.No Chapter Name English
1Lecture 1: Introduction to Online Learning –IDownload
Verified
2Lecture 2: Introduction to Online Learning –IDownload
Verified
3Lecture 3: Basics of Statistical LearningDownload
Verified
4Lecture 4: Empirical risk minimization Download
Verified
5Lecture 5: Consistency Halving algorithm Download
Verified
6Lecture 6: Online Learnability Download
Verified
7Lecture 7: Standard Optimal Algorithm Download
Verified
8Lecture 8: Classification in unrealizability caseDownload
Verified
9Lecture 9: Covers Impossibility ResultDownload
Verified
10Lecture 10: Weighted Majority Download
Verified
11Lecture 11: Proof Weighted MajorityDownload
Verified
12Lecture 12: Full Information vs Bandit SettingDownload
Verified
13Lecture 13: Adversarial Bandit SettingDownload
Verified
14Lecture 14: Exponential Weights for Exploration and Exploitation AlgorithmDownload
Verified
15Lecture 15: Regret Bound of Exp3Download
Verified
16Lecture 16: Regret Bound of Exp3(Contd.)Download
Verified
17Lecture 17: Exp3.P and Exp3.IXDownload
Verified
18Lecture 18: Online Convex OptimisationDownload
Verified
19Lecture 19: Follow the Leader (FTL) AlgorithmDownload
Verified
20Lecture 20: Follow the Regularized LeaderDownload
Verified
21Lecture 21: Online Gradient DescentDownload
Verified
22Lecture 22: Strongly Convex FunctionDownload
Verified
23Lecture 23: FoReL with Strongly Convex RegulariserDownload
Verified
24Lecture 24: FoReL with Strongly Convex Regulariser (Contd.)Download
Verified
25Lecture 25: Euclidean and Entropy RegularizerDownload
Verified
26Lecture 26: Introduction to Stochastic BanditsDownload
Verified
27Lecture 27: Concentration InequalitiesDownload
Verified
28Lecture 28: Subgaussian Random VariableDownload
Verified
29Lecture 29: Regret Definition and Regret DecompositionDownload
Verified
30Lecture 30: Explore and Commit (ETC) AlgorithmDownload
Verified
31Lecture 31: Regret Analysis and ETCDownload
Verified
32Lecture 32: Optimism in the Face of UncertaintyDownload
Verified
33Lecture 33: Upper Confidence Bound AlgorithmDownload
Verified
34Lecture 34 : Regret Analysis of UCB Download
Verified
35Lecture 35 : Problem Dependent and Independent Bounds of UCB Download
Verified
36Lecture 36 : KL-UCB AlgorithmDownload
Verified
37Lecture 37 : Thompson Sampling - Brief DiscussionDownload
Verified
38Lecture 38 : Proof Idea of Lower Bounds - 1Download
Verified
39Lecture 39 : Proof Idea of Lower Bounds - 2 Download
Verified
40Lecture 40 : Proof of Lower Bound-1Download
Verified
41Lecture 41 : Proof of Lower Bound-2Download
Verified
42Lecture 42 : Stochastic Contextual Bandits Download
Verified
43Lecture 43 : Introduction to Stochastic Linear BanditsDownload
Verified
44Lecture 44 : Stochastic Linear BanditsDownload
Verified
45Lecture 45 : Regret Analysis of SLB-I Download
Verified
46Lecture 46 : Regret Analysis of SLB - II PDF unavailable
47Lecture 47 : Regret Analysis of SLB-III PDF unavailable
48Lecture 48 : Construction of Confidence Ellipsoid - IPDF unavailable
49Lecture 49 : Construction of Confidence Ellipsoids - IIPDF unavailable
50Lecture 50 : Adversarial Contextual Bandits - IPDF unavailable
51Lecture 51 : Adversarial Contextual Bandits IIPDF unavailable
52Lecture 52 : Exp4 AlgorithmPDF unavailable
53Lecture 53 : Regret of Exp4PDF unavailable
54Lecture 54 : Adversarial Linear BanditsPDF unavailable
55Lecture 55 : Exp3 for Adversarial Linear BanditsPDF unavailable
56Lecture 56 : Introduction to Pure Exploration and its lower boundsPDF unavailable
57Lecture 57 : Uniform ExplorationPDF unavailable
58Lecture 58 : KL-LUCBPDF unavailable
59Lecture 59 : Lil’ UCBPDF unavailable
60Lecture 60 : Lower Bound for Pure Exploration ProblemPDF unavailable


Sl.No Language Book link
1EnglishNot Available
2BengaliNot Available
3GujaratiNot Available
4HindiNot Available
5KannadaNot Available
6MalayalamNot Available
7MarathiNot Available
8TamilNot Available
9TeluguNot Available