Perturbative adaptive importance sampling for Bayesian LOO cross-validation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chang, Joshua C, Li, Xiangting, Su, Tianyi, Xu, Shixin, Yao, Hao-Ren, Porcino, Julia, Chow, Carson
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918407811629056
author Chang, Joshua C
Li, Xiangting
Su, Tianyi
Xu, Shixin
Yao, Hao-Ren
Porcino, Julia
Chow, Carson
author_facet Chang, Joshua C
Li, Xiangting
Su, Tianyi
Xu, Shixin
Yao, Hao-Ren
Porcino, Julia
Chow, Carson
contents Importance sampling (IS) is an efficient stand-in for model refitting in performing (LOO) cross-validation (CV) on a Bayesian model. IS inverts the Bayesian update for a single observation by reweighting posterior samples. The so-called importance weights have high variance -- we resolve this issue through adaptation by transformation. We observe that removing a single observation perturbs the posterior by $\mathcal{O}(1/n)$, motivating bijective transformations of the form $T(θ)=θ+ h Q(θ)$ for $0<h\ll 1.$ We introduce several such transformations: partial moment matching, which generalizes prior work on affine moment-matching with a tunable step size; log-likelihood descent, which partially invert the Bayesian update for an observation; and gradient flow steps that minimize the KL divergence or IS variance. The gradient flow and likelihood descent transformations require Jacobian determinants, which are available via auto-differentiation; we additionally derive closed-form expressions for logistic regression and shallow ReLU networks. We tested the methodology on classification ($n\ll p$), count regression (Poisson and zero-inflated negative binomial), and survival analysis problems, finding that no single transformation dominates but their combination nearly eliminates the need to refit.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08151
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Perturbative adaptive importance sampling for Bayesian LOO cross-validation
Chang, Joshua C
Li, Xiangting
Su, Tianyi
Xu, Shixin
Yao, Hao-Ren
Porcino, Julia
Chow, Carson
Methodology
Artificial Intelligence
Machine Learning
Spectral Theory
Statistics Theory
Importance sampling (IS) is an efficient stand-in for model refitting in performing (LOO) cross-validation (CV) on a Bayesian model. IS inverts the Bayesian update for a single observation by reweighting posterior samples. The so-called importance weights have high variance -- we resolve this issue through adaptation by transformation. We observe that removing a single observation perturbs the posterior by $\mathcal{O}(1/n)$, motivating bijective transformations of the form $T(θ)=θ+ h Q(θ)$ for $0<h\ll 1.$ We introduce several such transformations: partial moment matching, which generalizes prior work on affine moment-matching with a tunable step size; log-likelihood descent, which partially invert the Bayesian update for an observation; and gradient flow steps that minimize the KL divergence or IS variance. The gradient flow and likelihood descent transformations require Jacobian determinants, which are available via auto-differentiation; we additionally derive closed-form expressions for logistic regression and shallow ReLU networks. We tested the methodology on classification ($n\ll p$), count regression (Poisson and zero-inflated negative binomial), and survival analysis problems, finding that no single transformation dominates but their combination nearly eliminates the need to refit.
title Perturbative adaptive importance sampling for Bayesian LOO cross-validation
topic Methodology
Artificial Intelligence
Machine Learning
Spectral Theory
Statistics Theory
url https://arxiv.org/abs/2402.08151