/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

 www.daniellowengrub.com
[No title]
| | fa.bianp.net
On the Convergence of the Unadjusted Langevin Algorithm
3.5 parsecs away

Travel
| | 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 ...
| | elijahpotter.dev
Markov Chains Are the Original Language Models
4.5 parsecs away

Travel
| | Back in my day, we used math for autocomplete.
| | www.ethanepperly.com
Big Ideas in Applied Math: Markov Chains - Ethan N. Epperly
2.8 parsecs away

Travel
| | [AI summary] The user is discussing Markov Chain Monte Carlo (MCMC) methods, specifically the Metropolis-Hastings algorithm, applied to sampling from a distribution defined by a matrix $ A $. The focus is on the acceptance probability when transitioning between subsets $ S $ and $ S' $ of size $ k $, where the acceptance probability is determined by the ratio of determinants of submatrices of $ A $. The user is also exploring the computational complexity of these methods and their application to problems involving large matrices.
| | blog.ephorie.de
Create Texts with a Markov Chain Text Generator... and what this has to do with ChatGPT! - Learning Machines
12.9 parsecs away

Travel
| [AI summary] This blog post explains how Markov chain algorithms generate text and relates it to the workings of large language models like ChatGPT, emphasizing statistical prediction and natural language processing.