Introduction to Online Convex Optimization

TL;DR

This paper introduces online convex optimization as a robust, adaptive approach to optimization that learns from experience in complex, real-world environments where traditional methods are infeasible.

Contribution

It presents the concept of viewing optimization as a learning process that adapts over time, highlighting its importance and success across various practical applications.

Findings

Online convex optimization enables adaptive learning in complex environments.

This approach has led to significant practical successes.

It bridges the gap between theoretical models and real-world applications.

Abstract

This manuscript portrays optimization as a process. In many practical applications the environment is so complex that it is infeasible to lay out a comprehensive theoretical model and use classical algorithmic theory and mathematical optimization. It is necessary as well as beneficial to take a robust approach, by applying an optimization method that learns as one goes along, learning from experience as more aspects of the problem are observed. This view of optimization as a process has become prominent in varied fields and has led to some spectacular success in modeling and systems that are now part of our daily lives.