Adventures in Linear Algebra++ and Unsupervised Learning

on YouTube ↗01h 00m

" summary

Explores connections between advanced linear algebra techniques and unsupervised learning, focusing on how linear-algebraic tools can be used to design or analyze algorithms for unsupervised tasks. Discusses specific mathematical frameworks and methods from linear algebra that inform algorithmic approaches in unsupervised learning.

AI-written summary · about

" chapters (17)

1. 0:00Intro
2. 1:04Is NP-hardness an obstacle for theory?
3. 3:59Classical Lin. Algebra: least square variants
4. 4:41Semi-classical linear algebra
5. 12:06Tensor variants of spectral methods
6. 14:03Main paradigm for unsupervised Learning
7. 16:46Inverse Moment Problem
8. 18:49Topic Models
9. 19:37"Bag of words" Assumption in Text Analysis
10. 20:33Hidden Variable Explanation
11. 40:17Ex 3: Dictionary Learning (aka Sparse Coding)
12. 41:59Why dictionary learning? Olshausen Field '96
13. 44:53"Energy minimization" heuristic
14. 50:09Understanding "randomly-wired" deep nets
15. 53:36Example of a useful ingredient
16. 54:56Open Problems (LinAL++)
17. 56:56Open Problems (ML)

" related talks

• 32mA Primer (or Refresher) On Linear Algebra for Data ScienceRuben van de Geer · PyData London 2019
• 34mThe Linear Algebra of Deep LearningElizabeth Ramírez · ScaleConf Colombia 2019
• 35mA Crash Course in Applied Linear AlgebraPatrick Landreman · PyData New York City 2019
• 01h 02mTheory and Big DataRavi Kannan · Big Data Boot Camp 2013
• 32mRandomized Numerical Linear Algebra: OverviewPetros Drineas · Randomized Numerical Linear Algebra and Applications 2018
• 43mThe Linear Algebra of Deep LearningElizabeth Ramírez · Code Mesh LDN 2020
• 01h 15mstd::linalg: Linear Algebra Coming to Standard C++Mark Hoemmen · CppCon 2023
• 01h 03mSampling for Linear Algebra, Statistics, and Optimization IMichael Mahoney · Foundations of Data Science Boot Camp 2018