Measuring Sample Quality with Kernels

Speaker: Lester Mackey , MSR

Date: Wednesday, March 15, 2017

Time: 4:00 PM to 5:00 PM Note: all times are in the Eastern Time Zone

Refreshments: 4:00 PM

Public: Yes

Location: 32-D463

Event Type:

Room Description:

Host: Stefanie Jegelka

Contact: Stefanie S. Jegelka,

Relevant URL:

Speaker URL: None

Speaker Photo:

Reminders to:

Reminder Subject: TALK: Measuring Sample Quality with Kernels

Approximate Markov chain Monte Carlo (MCMC) offers the promise of more rapid sampling at the cost of more biased inference. Since standard MCMC diagnostics fail to detect these biases, researchers have developed computable Stein discrepancy measures that provably determine the convergence of a sample to its target distribution. This approach was recently combined with the theory of reproducing kernels to define a closed-form kernel Stein discrepancy (KSD) computable by summing kernel evaluations across pairs of sample points. We develop a theory of weak convergence for KSDs based on Stein's method, demonstrate that commonly used KSDs fail to detect non-convergence even for Gaussian targets, and show that kernels with slowly decaying tails provably determine convergence for a large class of target distributions. The resulting convergence-determining KSDs are suitable for comparing biased, exact, and deterministic sample sequences and simpler to compute and parallelize than alternative Stein discrepancies. We use our tools to compare biased samplers, select sampler hyperparameters, and improve upon existing KSD approaches to one-sample hypothesis testing and sample quality improvement.

Research Areas:

Impact Areas:

See other events that are part of the Machine Learning Seminar Series.

Created by Stefanie S. Jegelka Email at Friday, March 10, 2017 at 1:11 PM.