Saved in:
Bibliographic Details
Main Authors: Zhang, Shunzhi, Liao, Shichen, Han, Congying, Guo, Tiande
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.15526
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917415738146816
author Zhang, Shunzhi
Liao, Shichen
Han, Congying
Guo, Tiande
author_facet Zhang, Shunzhi
Liao, Shichen
Han, Congying
Guo, Tiande
contents We study unconstrained smooth convex optimization under stochastic first- and zeroth-order oracles subject only to finite-moment bounds, naturally admitting persistent bias and heavy-tailed noise. In this hostile environment, integrating momentum into \emph{adaptive step search} to secure acceleration poses an inherent structural challenge, because momentum propagates oracle errors across iterations, inevitably undermining the stabilizing effect of local search. To address this difficulty, we propose \texttt{RAAS}, a robust accelerated adaptive search method with tunable momentum intervention. Theoretically, we develop a general high-probability framework for adaptive search methods under stochastic oracle feedback, and instantiate it through the strongly convex and general convex analyses of \texttt{RAAS}. This yields high-probability stopping-time complexity bounds for reaching the attainable precision neighborhood. The resulting guarantees also clarify how the algorithmic parameters trade off early-stage acceleration against late-stage stability, and motivate a simple switching heuristic that performs well empirically.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15526
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Accelerated Adaptive Search: High-Probability Complexity Bounds under Bounded-Moment Stochastic Oracles
Zhang, Shunzhi
Liao, Shichen
Han, Congying
Guo, Tiande
Optimization and Control
We study unconstrained smooth convex optimization under stochastic first- and zeroth-order oracles subject only to finite-moment bounds, naturally admitting persistent bias and heavy-tailed noise. In this hostile environment, integrating momentum into \emph{adaptive step search} to secure acceleration poses an inherent structural challenge, because momentum propagates oracle errors across iterations, inevitably undermining the stabilizing effect of local search. To address this difficulty, we propose \texttt{RAAS}, a robust accelerated adaptive search method with tunable momentum intervention. Theoretically, we develop a general high-probability framework for adaptive search methods under stochastic oracle feedback, and instantiate it through the strongly convex and general convex analyses of \texttt{RAAS}. This yields high-probability stopping-time complexity bounds for reaching the attainable precision neighborhood. The resulting guarantees also clarify how the algorithmic parameters trade off early-stage acceleration against late-stage stability, and motivate a simple switching heuristic that performs well empirically.
title Robust Accelerated Adaptive Search: High-Probability Complexity Bounds under Bounded-Moment Stochastic Oracles
topic Optimization and Control
url https://arxiv.org/abs/2604.15526