Summary of Scalable Bayesian Learning with Posteriors, by Samuel Duffield et al.
Scalable Bayesian Learning with posteriors
by Samuel Duffield, Kaelan Donatella, Johnathan Chiu, Phoebe Klett, Daniel Simpson
First submitted to arxiv on: 31 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
Summary difficulty | Written by | Summary |
---|---|---|
High | Paper authors | High Difficulty Summary Read the original abstract here |
Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces posteriors, a PyTorch library that enables scalable Bayesian learning by approximating high-dimensional posterior distributions. The authors present tempered stochastic gradient Markov chain Monte Carlo, which seamlessly transitions into optimization and ensures unbiased Bayesian posterior estimates for deep ensembles. Experiments demonstrate the utility of Bayesian approximations, including investigating the cold posterior effect and large language model applications. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper makes machine learning more accessible by creating a library that helps with complex mathematical calculations. It also improves how we use deep learning models to make predictions. The authors show that their ideas work well in practice by testing them on different tasks and data sets. |
Keywords
» Artificial intelligence » Deep learning » Large language model » Machine learning » Optimization