Backfitting for large scale crossed random effects regressions

07/21/2020
by   Swarnadip Ghosh, et al.
0

Regression models with crossed random effect error models can be very expensive to compute. The cost of both generalized least squares and Gibbs sampling can easily grow as N^3/2 (or worse) for N observations. Papaspiliopoulos et al. (2020) present a collapsed Gibbs sampler that costs O(N), but under an extremely stringent sampling model. We propose a backfitting algorithm to compute a generalized least squares estimate and prove that it costs O(N) under greatly relaxed though still strict sampling assumptions. Empirically, the backfitting algorithm costs O(N) under further relaxed assumptions. We illustrate the new algorithm on a ratings data set from Stitch Fix.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2021

Scalable logistic regression with crossed random effects

The cost of both generalized least squares (GLS) and Gibbs sampling in a...
research
03/26/2018

Scalable inference for crossed random effects models

We analyze the complexity of Gibbs samplers for inference in crossed ran...
research
02/20/2023

Gibbs Sampler for Matrix Generalized Inverse Gaussian Distributions

Sampling from matrix generalized inverse Gaussian (MGIG) distributions i...
research
03/04/2020

Fast sampling from β-ensembles

We study sampling algorithms for β-ensembles with time complexity less t...
research
03/29/2022

Direct Sampling with a Step Function

The direct sampling method proposed by Walker et al. (JCGS 2011) can gen...
research
11/29/2022

Linear Complexity Gibbs Sampling for Generalized Labeled Multi-Bernoulli Filtering

Generalized Labeled Multi-Bernoulli (GLMB) densities arise in a host of ...
research
07/23/2023

Scalable solution to crossed random effects model with random slopes

The crossed random-effects model is widely used in applied statistics, f...

Please sign up or login with your details

Forgot password? Click here to reset