Statistician Sam Power publishes 30+ PDF notes on MCMC, sampling and generative models
dianarycai · x · 2026-10-15
Researcher Sam Power says he has mostly stopped blogging and instead publishes marginally more formal write-ups as PDFs on his site — 30+ notes, each with a GitHub link. Topics include Hamiltonian Monte Carlo with finite differences, MCMC without Metropolis-Hastings, analysis of speculative sampling, direct vs indirect generative models, sub-Gamma/Bernstein concentration bounds, Poincaré constants, Ziggurat rejection sampling, online mean/variance via Kalman filtering, and geometric ergodicity of Markov chains. A worthwhile stash for anyone in statistical computing and generative modeling theory.
More from Research
- Curated roundup: frontier models help crack decades-old problems across disciplines — IgorCarron · 2026-10-15
- Stanford's CausalSmith automates causal inference research with Lean-verified proofs — StanfordAILab · 2026-10-15
- Cellular Intelligence wins Best Poster at scverse 2026 for perturbation platform — arjunrajlab · 2026-10-15
- BARRACUDA microfluidic chip traps a million single cells to map gene circuit design space at scale — NikoMcCarty · 2026-10-15
- Stanford's DexAgent turns one human egocentric video into dexterous robot training data — StanfordAILab · 2026-10-15
- Johns Hopkins wins HCOMP 2026 Best Paper for reader-centered summarization evaluation — mdredze · 2026-10-15