Beyond Gradient Fidelity in Gaussian Precision Learning

Matching the gradient does not determine the value of a finite update in Gaussian precision learning. We show how componentwise inverse information preserves gains that parameter-wise separation loses, and quantify how local approximation accuracy can fail to preserve those gains. For positive affine precision models, retaining prior–posterior cancellation yields a reciprocal minorizer that preserves shared-update geometry and supports boundary activations lost by separation. On two natural instances, certified component-model gains exceed the separated models' global optima by at least 12.37 and 42.70 nats. The approximation limit is sharper still: reciprocal models can agree in old value, gradient and Hessian, with a factor-two remainder envelope, yet select actions retaining only an inverse-linear fraction of available gain. Bounding feasible edge ratios restores a matching-order guarantee, establishing Θ(T⁻¹) worst-case dependence on action scale for the factor-two class. In a Gaussian realization, the retained fraction of actual likelihood gain also vanishes. Original-matrix certificates carry the analysis into executed updates: complete rounded learning paths attain gains of 158.63 and 134.13 nats. These results identify finite-action value as a criterion for choosing what inverse information a learning algorithm retains.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-13
DOI
https://doi.org/10.5281/zenodo.24199541
Primary Topic
Gaussian Processes and Bayesian Inference
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Beyond Gradient Fidelity in Gaussian Precision Learning

Xu Cao, Wenxuan Xiao
1 links
Zenodo (CERN European Organization for Nuclear Research)
Gaussian Processes and Bayesian Inference
preprint

Beyond Gradient Fidelity in Gaussian Precision Learning

Xu Cao, Wenxuan Xiao
preprint en

Abstract

Matching the gradient does not determine the value of a finite update in Gaussian precision learning. We show how componentwise inverse information preserves gains that parameter-wise separation loses, and quantify how local approximation accuracy can fail to preserve those gains. For positive affine precision models, retaining prior–posterior cancellation yields a reciprocal minorizer that preserves shared-update geometry and supports boundary activations lost by separation. On two natural instances, certified component-model gains exceed the separated models' global optima by at least 12.37 and 42.70 nats. The approximation limit is sharper still: reciprocal models can agree in old value, gradient and Hessian, with a factor-two remainder envelope, yet select actions retaining only an inverse-linear fraction of available gain. Bounding feasible edge ratios restores a matching-order guarantee, establishing Θ(T⁻¹) worst-case dependence on action scale for the factor-two class. In a Gaussian realization, the retained fraction of actual likelihood gain also vanishes. Original-matrix certificates carry the analysis into executed updates: complete rounded learning paths attain gains of 158.63 and 134.13 nats. These results identify finite-action value as a criterion for choosing what inverse information a learning algorithm retains.

Zenodo (CERN European Organization for Nuclear Research)
Gaussian Processes and Bayesian Inference
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon