Skip to main content

Statistics Seminar

Advances in Distribution Compression by Lester Mackey

Event Details

Wednesday, December 7, 2022
4-5 p.m.

Date: December 7, 2022

Speaker: Lester Mackey


Note: Virtual

Zoom link:

Title: Advances in Distribution Compression

Abstract: This talk will introduce three new tools for summarizing a probability distribution more effectively than independent sampling or standard Markov chain Monte Carlo thinning:

1.       Given an initial n point summary (for example, from independent sampling or a Markov chain), kernel thinning finds a subset of only square-root n points with comparable worst-case integration error across a reproducing kernel Hilbert space.

2.       If the initial summary suffers from biases due to off-target sampling, tempering, or burn-in, Stein thinning simultaneously compresses the summary and improves the accuracy by correcting for these biases.

3.       Finally, Compress++ converts any unbiased quadratic-time thinning algorithm into a near-linear-time algorithm with comparable error.

These tools are especially well-suited for tasks that incur substantial downstream computation costs per summary point like organ and tissue modeling in which each simulation consumes 1000s of CPU hours.