The Power of Sampling by Peter W. Glynn

The Power of Sampling by Peter W. Glynn

International Centre for Theoretical Sciences via YouTube Direct link

Why?

17 of 45

17 of 45

Why?

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

The Power of Sampling by Peter W. Glynn

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Date: 14 August 2019, 16:00 to
  2. 2 Introduction to speaker
  3. 3 The Power of Sampling
  4. 4 What should a well-educated scientist know about sampling?
  5. 5 Thesis of Lecture:
  6. 6 According to Wikipedia:
  7. 7 Some History:
  8. 8 First sampling-based survey:
  9. 9 Second known instance of sampling
  10. 10 Today, statistical sampling is used everywhere
  11. 11 Such randomized trials form one setting where one can legitimately claim evidence of a causal effect
  12. 12 Key Philosophical Underpinning:
  13. 13 1936 US Presidential Election
  14. 14 Problems with Literary Digest survey:
  15. 15 Moral of the Story:
  16. 16 Subtle modifications in sampling can have a big impact
  17. 17 Why?
  18. 18 Many other such subtleties exist in applying sampling methods
  19. 19 Active research area:
  20. 20 Sampling in Computational Mathematics
  21. 21 High-dimensional Integration:
  22. 22 High-level Perspective:
  23. 23 History
  24. 24 Analysis of Monte Carlo Method:
  25. 25 If it's so slow, why is it so widely used?
  26. 26 The Numerical Alternative to Monte Carlo
  27. 27 Better integration rules:
  28. 28 Tracking discontinuities is easy in d = 1
  29. 29 Versatility of Monte Carlo Method:
  30. 30 "Curse of Dimensionality"
  31. 31 Result
  32. 32 What about Monte Carlo?
  33. 33 Example: Compute volume of region A c [0, 1]d
  34. 34 So, Monte Carlo is dimensionally insensitive...
  35. 35 Coding Flexibility and Visualization: Aan Example
  36. 36 Modify model so that time spent in just one state is non-exponential...
  37. 37 Monte Carlo Alternative:
  38. 38 A Key Difference between Statistical Sampling and Monte Carlo Sampling
  39. 39 Sampling in Synthesizing Distributed Controls
  40. 40 The agents typically need state information to make good decisions
  41. 41 Example: Assigning incoming jobs to servers on a server farm
  42. 42 Approach 1: Centralized controller assigns incoming jobs to shortest queue
  43. 43 Sampling plays a key role in many machine learning algorithms
  44. 44 Final words:
  45. 45 Q&A

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.