The Query Complexity of Unknown Sparse Gradient Residuals

We study optimization of an average of \(n\) functions when gradient predictions are exact except for at most \(k\) unknown components. An initial scan may miss these exceptions. For a class of smooth problems, we prove that the optimal worst-case expected number of component-gradient evaluations needed to find an approximate stationary point is \[ Θ\!\left(\min\left\{nk+\mathcal R,\frac nk\mathcal R\right\}\right), \] where \(\mathcal R\) represents the optimal cost when the exceptional components are known. Prediction evaluations are free. This bound shows that discovering even a few exceptions can cost more than one full scan and can account for most of the gradient evaluations.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16638
Primary Topic
Stochastic Gradient Optimization Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

The Query Complexity of Unknown Sparse Gradient Residuals

Yuriy V. Dorn
arXiv (Cornell University)
Stochastic Gradient Optimization Techniques
preprint

The Query Complexity of Unknown Sparse Gradient Residuals

Yuriy V. Dorn
preprint en

Abstract

We study optimization of an average of \(n\) functions when gradient predictions are exact except for at most \(k\) unknown components. An initial scan may miss these exceptions. For a class of smooth problems, we prove that the optimal worst-case expected number of component-gradient evaluations needed to find an approximate stationary point is \[ Θ\!\left(\min\left\{nk+\mathcal R,\frac nk\mathcal R\right\}\right), \] where \(\mathcal R\) represents the optimal cost when the exceptional components are known. Prediction evaluations are free. This bound shows that discovering even a few exceptions can cost more than one full scan and can account for most of the gradient evaluations.

arXiv (Cornell University)
Stochastic Gradient Optimization Techniques
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