New work with the Pyro team (https://t.co/6en944fTtd) on efficient batched discrete variable inference through tensor variable elimination.— harvardnlp (@harvardnlp) February 13, 2019
Practically generalizes 'einsum' with batching, semirings (log-space, max, etc), and marginals. Powers Pyro's discrete directed inference. pic.twitter.com/upE6Soazkw
Have you ever wanted to see seven different Bayesian and frequentist ways to measure the avg difference between two groups? Check out my new post to see examples of standard #rstats t-tests, the infer package, brms regression, and raw @mcmc_stan code! https://t.co/U2sjL9nt6b pic.twitter.com/OgK1zsQXiY— Andrew Heiss, PhD (@andrewheiss) January 29, 2019
Interested in statistical methods for data science? Check out our probabilistic programming and bayesian methods playlist, including:— PyData (@PyData) January 20, 2019
"Bayesian Network Modeling using R and Python" by Pragyansmita Nayak: https://t.co/CNw92p8jAJ
Don't forget to subscribe to #PyData on Youtube!
Statistical thought of the day: I don't embrace the Bayesian paradigm because it is without problems. I embrace it because (1) it solves the most problems and (2) null hypothesis significance testing, p-values, and type I error are beyond repair. Mixing Bayes+frequentist=mess.— Frank Harrell (@f2harrell) January 8, 2019