Subject
32 entries
Bayesian
Bookmarks
Quant-MELO-Portfolio: Bayesian Portfolio Optimization
Quant-MELO-Portfolio is a Python project applying Bayesian architecture to stock portfolio optimization — finding optimal weights via Global Minimum Variance and Tangency portfolios. A concrete implementation of mean-variance optimization with Bayesian uncertainty quantification.
Probabilistic Machine Learning (Kevin Murphy)
Kevin Murphy's Probabilistic Machine Learning book series — a comprehensive treatment of ML through a probabilistic/Bayesian lens, freely available online. The 2012 original (MLPP) and its 2022 follow-ups are standard graduate-level references.
What Are the Most Important Statistical Ideas of the Past 50 Years?
Andrew Gelman and Aki Vehtari's 2021 JASA paper enumerating 8 ideas that most changed statistics in the past 50 years — from counterfactual causal inference to bootstrapping to overparameterized models. A rare high-level synthesis by two of the field's most credible voices.
Regression and Other Stories
Regression and Other Stories by Gelman, Hill, and Vehtari is a practical statistics textbook covering regression modeling from basics through causal inference — grounded in real data examples and the Bayesian workflow. The modern standard for applied regression.
Probabilistic Machine Learning: An Introduction (Murphy)
Kevin Murphy's Probabilistic Machine Learning: An Introduction is the modern update to his 2012 ML textbook — free online, covering everything from linear models through deep learning with a probabilistic framing. The definitive graduate-level ML reference for 2022 onward.
A Multi-Level Bayesian Analysis of Racial Bias in Police Shootings
A PLOS ONE paper applying multi-level Bayesian hierarchical models to police shooting data across US counties from 2011–2014, finding significant racial disparities in lethal force use. Notable for applying rigorous statistical methods to a politically charged dataset.
Surfing Silver: Dynamic Bayesian Forecasting for Fun and Profit
Slides from a Data Popup talk on dynamic Bayesian forecasting — applying Bayesian state-space models to time series prediction with uncertainty quantification. One of the cleaner practitioner introductions to Bayesian time series methods from the mid-2010s data science speaker circuit.
Understanding Bayes: How to Become a Bayesian in Eight Easy Steps
Alexander Etz's eight-step guide to adopting Bayesian thinking in statistics — covers prior selection, Bayes factors, and the core philosophical shift from frequentist null-hypothesis testing. A practical on-ramp for scientists trained in classical statistics.
How a Kalman Filter Works, in Pictures
The clearest visual explanation of how a Kalman filter works — building from Gaussian distributions to the prediction-update cycle without losing the intuition in the math. A reference that makes the algorithm genuinely understandable rather than just computable.
Statistical Inference for Everyone
Statistical Inference for Everyone (SIE) is a free introductory statistics textbook by Brian Blais that teaches through examples and probability rather than formulas. Recommended as a gentler alternative to frequentist-heavy introductory texts.
Bayesian Regression with PyMC: A Brief Tutorial
A Zipfian Academy student's tutorial on Bayesian linear regression using PyMC — notable both as an accessible introduction to probabilistic modeling and as a window into the Zipfian cohort's learning culture of public writing. PyMC was the dominant Python tool for Bayesian modeling at the time.
Zipfian Academy: Week 2 — Or: "A Frequentist and a Bayesian Walk into a Bar..."
A Zipfian Academy student's week 2 post, titled 'A Frequentist and a Bayesian Walk into a Bar' — covering the pivotal statistics week where bootcamp students confronted the philosophical divide between frequentist and Bayesian approaches. One of the most memorable weeks in the curriculum.
What Bayesianism Taught Me
A LessWrong post on what Bayesian reasoning changed about the author's thinking — not the mechanics of Bayes' theorem but the epistemic habits it instills. Treating beliefs as probability distributions rather than binary true/false is the core insight.
Programmatically Understanding the Expectation Maximization Algorithm
Nipun Batra's programmatic walkthrough of the Expectation Maximization algorithm — showing the E and M steps in code to build intuition for how EM converges. Makes the algorithm's alternating optimization structure tangible.
Outlier Detection via Markov Chain Monte Carlo
Bugra Akyildiz's walkthrough of outlier detection using Markov Chain Monte Carlo via PyMC — fitting a Bayesian mixture model to separate inliers from outliers using posterior inference. A more principled alternative to distance-based outlier methods.
MH370 MCMC Notebook — Conor Myhrvold
Conor Myhrvold's IPython notebook using Monte Carlo simulation to analyze the probable flight path of MH370 from satellite pings. An early high-profile example of using Bayesian inference and simulation for real-world analysis.
Frequentism and Bayesianism: A Practical Introduction
Jake VanderPlas's Python-driven comparison of frequentist and Bayesian statistics — showing the two philosophies side-by-side with code. The most-cited accessible treatment of a distinction that confuses most practitioners.
German Tank Problem
The German tank problem: WWII Allies estimated German tank production by applying statistical estimation to captured tank serial numbers. A compelling historical case study in the power of statistical inference over conventional intelligence methods.
A/B Test Calculator — ABBA (Thumbtack)
Thumbtack's ABBA (A/B Analysis) tool — a Bayesian A/B test calculator that reports the probability one variant beats another, rather than traditional p-values. Practically more useful than frequentist tests for the decisions product teams actually make.
Optimal Thompson Sampling: Asymptotic Analysis
Emilie Kaufmann's arXiv paper on the asymptotic optimality of Thompson Sampling for multi-armed bandits — the theoretical grounding that explains why Thompson Sampling works as well as it does empirically. Proves it achieves near-optimal regret bounds.
Multi-Armed Bandits
Cameron Davidson-Pilon's blog post on multi-armed bandits from a Bayesian perspective — draws on the same probabilistic programming intuition as his 'Bayesian Methods for Hackers' book. Frames bandits as the natural application of iterative belief updating.
The Importance of Sequential Testing
Austin Rochford's introduction to sequential testing — the SPRT and Bayesian alternatives to fixed-horizon A/B tests that let you stop early when results are clear without inflating false positive rates.
Metacademy — Bayesian Machine Learning Roadmap
Roger Grosse's curated Metacademy roadmap for learning Bayesian machine learning from scratch — a sequenced path through Bayesian inference, probabilistic graphical models, approximate inference, and nonparametric methods. The systematic route through a complex prerequisite landscape.
A/B Testing with Bayesian Bandits in Google Analytics
FastML walkthrough of Google Analytics Content Experiments — which use a multi-armed bandit algorithm instead of fixed 50/50 splits to dynamically allocate traffic toward better-performing variants. A practical introduction to bandit-based online optimization.
Metacademy
Metacademy is a 'web of knowledge' for machine learning — a dependency graph of concepts where each node links to learning resources and its prerequisites. The idea: show exactly what you need to know before you can understand any given topic.
Bayesian Machine Learning via Category Theory
Culbertson and Sturtz's 2013 paper applying category theory to Bayesian machine learning — using the Kleisli category of the Giry monad to formalize supervised learning, stochastic processes as priors, and the Kalman filter. Heavy theory, but part of the broader push to give probabilistic ML rigorous foundations.
BayesDB
BayesDB from MIT CSAIL's probabilistic computing group — a database system that lets you query statistical relationships using a SQL-like language (BQL) without specifying a model. Automatically infers the right probabilistic model from data.
Bayesian Statistical Analysis with PyMC
PyTennessee 2013 presentation on Bayesian statistical analysis with PyMC — introducing probabilistic programming in Python as a practical alternative to frequentist methods. PyMC let practitioners write down generative models and get MCMC inference without implementing samplers from scratch.
An Introduction to Data Analysis — Statistics Done Wrong
Alex Reinhart's 'Statistics Done Wrong' introduction to data analysis — opens with the key insight that a p-value measures surprise, not correctness. A corrective for scientists trained in classical statistics who misinterpret their own results.
Flipping a Coin: Bayesian Updating of Probability Distributions
A walkthrough of Bayesian probability updating using coin flipping — showing how a prior distribution over coin bias is updated with each flip observation. The cleanest possible introduction to Bayesian reasoning as a process.
Bayesian Methods for Hackers
Cameron Davidson-Pilon's open-source book teaching Bayesian inference through computational examples in Python, using PyMC3 for probabilistic programming. The approach is computation-first rather than math-first — ideal for programmers who want to apply Bayesian reasoning without heavy statistics background.
Bayes' Theorem: Conditional Probabilities
A Vassarstats reference page on Bayes' Theorem and conditional probabilities. The theorem is the backbone of Bayesian reasoning: updating prior beliefs with new evidence to get a posterior probability.