A Classical Algorithm Framework for Dequantizing Quantum Machine Learning

A Classical Algorithm Framework for Dequantizing Quantum Machine Learning

Simons Institute via YouTube Direct link

All we need are RUR decompositions

10 of 16

10 of 16

All we need are RUR decompositions

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

A Classical Algorithm Framework for Dequantizing Quantum Machine Learning

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

  1. 1 Intro
  2. 2 Dequantizing quantum lipear algebra
  3. 3 Unifying quantum linear algebra
  4. 4 Matrix notation
  5. 5 Input/output assumptions of QML
  6. 6 Powering up classical computation with measurements
  7. 7 Sample and query access
  8. 8 Quantum-inspired sketching, aka importance sampling
  9. 9 Importance sampling can approximate matrix products
  10. 10 All we need are RUR decompositions
  11. 11 Main theorem: even singular value transformation
  12. 12 Proof sketch of main theprem
  13. 13 Interpreting the even SVT result
  14. 14 Comparing quantum-inspired SVT to quantum SVT
  15. 15 Applications
  16. 16 Implications for exponential speedups in QML

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.