Saved in:
Bibliographic Details
Main Authors: Polson, Sarah, Sokolov, Vadim
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.05032
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911422263328768
author Polson, Sarah
Sokolov, Vadim
author_facet Polson, Sarah
Sokolov, Vadim
contents Modern training and inference pipelines in statistical learning and deep learning repeatedly invoke linear-system solves as inner loops, yet high-accuracy deterministic solvers can be prohibitively expensive when solves must be repeated many times or when only partial information (selected components or linear functionals) is required. We position \emph{Monte Carlo boosting} as a practical alternative in this regime, surveying random-walk estimators and sequential residual correction in a unified notation (Neumann-series representation, forward/adjoint estimators, and Halton-style sequential correction), with extensions to overdetermined/least-squares problems and connections to IRLS-style updates in data augmentation and EM/ECM algorithms. Empirically, we compare Jacobi and Gauss--Seidel iterations with plain Monte Carlo, exact sequential Monte Carlo, and a subsampled sequential variant, illustrating scaling regimes that motivate when Monte Carlo boosting can be an enabling compute primitive for modern statistical learning workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05032
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fast Compute via MC Boosting
Polson, Sarah
Sokolov, Vadim
Computation
Modern training and inference pipelines in statistical learning and deep learning repeatedly invoke linear-system solves as inner loops, yet high-accuracy deterministic solvers can be prohibitively expensive when solves must be repeated many times or when only partial information (selected components or linear functionals) is required. We position \emph{Monte Carlo boosting} as a practical alternative in this regime, surveying random-walk estimators and sequential residual correction in a unified notation (Neumann-series representation, forward/adjoint estimators, and Halton-style sequential correction), with extensions to overdetermined/least-squares problems and connections to IRLS-style updates in data augmentation and EM/ECM algorithms. Empirically, we compare Jacobi and Gauss--Seidel iterations with plain Monte Carlo, exact sequential Monte Carlo, and a subsampled sequential variant, illustrating scaling regimes that motivate when Monte Carlo boosting can be an enabling compute primitive for modern statistical learning workflows.
title Fast Compute via MC Boosting
topic Computation
url https://arxiv.org/abs/2602.05032