Bounds for the Tracking Error and Dynamic Regret of Inexact Online Optimization Methods: A General Analysis via Sequential Semidefinite Programs

TL;DR

This paper introduces a unified control-theoretic framework using sequential semidefinite programs to analyze and derive exact bounds for tracking error and dynamic regret in various inexact online optimization algorithms.

Contribution

It provides a novel, unified approach with exact analytical solutions for tracking error bounds across multiple inexact online optimization methods.

Findings

Derived exact tracking error bounds for several online algorithms.

Developed a routine to convert tracking error bounds into dynamic regret bounds.

Unified analysis applicable under various inexact oracle assumptions.

Abstract

In this paper, we develop a unified framework for analyzing the tracking error and dynamic regret of inexact online optimization methods under a variety of settings. Specifically, we leverage the quadratic constraint approach from control theory to formulate sequential semidefinite programs (SDPs) whose feasible points naturally correspond to tracking error bounds of various inexact online optimization methods including the inexact online gradient descent (OGD) method, the online gradient descent-ascent method, the online stochastic gradient method, and the inexact proximal online gradient method. We provide exact analytical solutions for our proposed sequential SDPs, and obtain fine-grained tracking error bounds for the online algorithms studied in this paper. We also provide a simple routine to convert the obtained tracking error bounds into dynamic regret bounds. The main novelty of our analysis is that we derive exact analytical solutions for our proposed sequential SDPs under various inexact oracle assumptions in a unified manner.