Explore >> Select a destination
|
You are here 
|
www.ethanrosenthal.com | ||
| | | | |
lukesingham.com
|
|
| | | | | This post goes through a binary classification problem with Python's machine learning library scikit-learn. | |
| | | | |
matbesancon.xyz
|
|
| | | | | Learning by doing: predicting the outcome. | |
| | | | |
dfm.io
|
|
| | | | | [AI summary] This document provides a comprehensive guide to estimating autocorrelation times in Markov Chain Monte Carlo (MCMC) simulations. It begins by explaining the importance of autocorrelation in MCMC and how it affects the effective sample size. The text then introduces several methods for estimating autocorrelation times, including the Goodman & Weare (2010) method and a newer algorithm developed by the author (DFM 2017). The document also discusses the limitations of these methods with short chains and introduces a maximum likelihood approach using the celerite library to fit an autocorrelation model. Finally, it concludes with recommendations for choosing appropriate chain lengths based on the estimated autocorrelation times. | |
| | | | |
jonathanweisberg.org
|
|
| | | Jonathan Weisberg's Homepage | ||
