Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		francisbach.com Rethinking SGD's noise - Machine Learning Research Blog
\|	\|	fa.bianp.net On the Convergence of the Unadjusted Langevin Algorithm The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of some machine learning methods such as diffusion models and differentially private learning. In this post, I'll derive a simple convergence analysis of this method in the special case when the ...	2.8 parsecs Travel
\|	\|
\|	\|	windowsontheory.org A blitz through classical statistical learning theory - Windows On Theory Previous post: ML theory with bad drawings Next post: What do neural networks learn and when do they learn it, see also all seminar posts and course webpage. Lecture video (starts in slide 2 since I hit record button 30 seconds too late - sorry!) - slides (pdf) - slides (Powerpoint with ink and animation)...	3.3 parsecs Travel
\|	\|
\|	\|	bdtechtalks.com A simple guide to gradient descent in machine learning - TechTalks Gradient descent is the main technique for training machine learning and deep learning models. Read all about it.	3.3 parsecs Travel
\|	\|
\|	\|	www.countbayesie.com Working with Probability Distributions - Count Bayesie Learn about Discrete and Continuous probability distributions as well as the types of questions that they can both answers. This post also discusses the relationship between the Binomial and Beta distributions.	11.2 parsecs Travel
\|