Completed
Ridge regression on MNIST
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Are Gaussian Data All You Need for Machine Learning Theory - A Statistical Physics Perspective
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The machine learning revolutic
- 3 Gaussians data
- 4 Physicists & Theoretical Neuroscie
- 5 Random Matrix Theory, Statistics
- 6 Data agnostic approaches
- 7 Fitting real dataset with a Gaussian model
- 8 Ridge regression on MNIST
- 9 But Gaussian theory does not always work
- 10 Ridge, Logistic, Hinge classification vs Gaussian
- 11 What is a better model than a single Gaussian?
- 12 Theorem: Gaussian Mixture through random
- 13 Open problems: beyond proportional regim
- 14 Generative Neural Networks as a proxy for r
- 15 GAN generated data behaves as Gaussian Mi
- 16 GMM stays GMM through random features
- 17 Theorem: Asymptotic of the Gaussian Mixture mo
- 18 2 Gaussians vs 1 Gaussian for different teacher
- 19 Single Gaussian for randon
- 20 Remember this plot with random label?
- 21 Universality of phase transition for homoskedast
- 22 Ridge interpolator & random
- 23 Many more questions...
