Robustness Should Not Be at Odds with Accuracy - A Statistical Learning Theory Perspective

Robustness Should Not Be at Odds with Accuracy - A Statistical Learning Theory Perspective

Harvard CMSA via YouTube Direct link

Concluding remarks

13 of 13

13 of 13

Concluding remarks

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Robustness Should Not Be at Odds with Accuracy - A Statistical Learning Theory Perspective

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

  1. 1 Intro
  2. 2 Statistical Learning Theory
  3. 3 Adversarial Learning
  4. 4 Decomposition of the adversarial loss
  5. 5 Unexpected phenomena
  6. 6 Robustness at odds with accuracy
  7. 7 Choosing a suitable robustness parameter
  8. 8 The margin canonical Bayes predictor
  9. 9 Redefining the adversarial loss
  10. 10 Empirical adaptive robust loss
  11. 11 Adaptive robust data-augmentation
  12. 12 Adaptive data augmentation maintains consistency of
  13. 13 Concluding remarks

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.