Presentation is loading. Please wait.

Presentation is loading. Please wait.

A pre-Weekend Talk on Online Learning TGIF Talk Series Purushottam Kar.

Similar presentations


Presentation on theme: "A pre-Weekend Talk on Online Learning TGIF Talk Series Purushottam Kar."— Presentation transcript:

1 A pre-Weekend Talk on Online Learning TGIF Talk Series Purushottam Kar

2 Outline Some Motivating Examples Discovering customer preferences Learning investment profiles Detecting credit card fraud The Formal Online Learning Framework Notion of regret Formalization of motivating examples Simple Online Algorithms Online classification, regression Online ranking Batch solvers for large scale learning problems Other Feedback-based Learning Frameworks 2

3 Some Motivating Examples Why Online Learning can be Useful 3

4 The Cooks Dilemma 4

5 Discovering Customer Preferences 5 Loss

6 Learning Investment Profiles 6

7 Detecting Credit Card Fraud 7

8 The Formal Online Learning Framework How we assess Online Learning Algorithms 8

9 The Online Learning Model 9

10 Motivating Examples Revisited 10

11 Motivating Examples Revisited 11

12 Simple Online Algorithms What makes online learning click ? 12

13 Online Linear Classification 13

14 The Perceptron Algorithm in action 14

15 Online Regression 15

16 Online Regression via Online Gradient Descent 16

17 Online Bipartite Ranking 17

18 Batch Solvers 18

19 Batch Solvers 19

20 Other Feedback based Learning Frameworks Two axes of variation: modelling of environment and feedback Online Learning: some modelling of environment and full feedback Losses are simple functions over linear models (can be made non linear though) At each step the loss function itself is given to us: full information Models are agnostic: no realizability assumptions are made Multi-armed Bandits: weak modelling of environment, weak feedback Often no assumptions made on nature of loss function Limited feedback: only loss value on played action made available Contextual bandits try to model loss function but make realizability assumptions Reinforcement Learning: Strong modelling of environment, weak feedback Environment modelled as a state space with adaptive stochastic transitions Reward functions modeled as functions of state space and action Limited feedback available: need to learn, state space as well as reward function 20


Download ppt "A pre-Weekend Talk on Online Learning TGIF Talk Series Purushottam Kar."

Similar presentations


Ads by Google