Error-Sensitive Dynamic Calibration for Online Optimization with Switching Costs

Oloko, Toye O.; Talata, Zsolt; Hashemi, Morteza

Permalink

https://hdl.handle.net/2142/130290 Copy

Description

Title

Error-Sensitive Dynamic Calibration for Online Optimization with Switching Costs

Author(s)

• Oloko, Toye O.
• Talata, Zsolt
• Hashemi, Morteza

Issue Date

2025-09-17

Keyword(s)

• Online convex optimization
• Error-sensitive
• Dynamic calibration

Abstract

Neural networks (NNs) have achieved state-of-the-art performance in a wide range of applications; however, their deployment in online settings often exposes a lack of robustness due to various dynamic and uncertain conditions. In contrast, traditional online algorithms offer formal robustness guarantees, yet generally do not attain the predictive accuracy of modern neural network models. To address this trade-off, we propose a novel neural network architecture that incorporates a dynamic calibration layer, designed to enhance robustness in online environments without sacrificing predictive performance. The proposed dynamic calibration layer consists of a differentiable optimization component that adjusts the NN output in real time, enabling end-to-end training via standard backpropagation. We provide theoretical analysis establishing performance bounds relative to an offline optimal benchmark. Next, we leverage these bounds to constrain the function class used for dynamic calibration, ensuring both practical feasibility and theoretical soundness. Empirical evaluation is conducted on a real-world case study involving data center energy management. Comparative results against existing online and hybrid approaches demonstrate that our architecture consistently outperforms baseline methods, both in terms of average performance and robustness measured in terms of competitive ratio.

Publisher

Allerton Conference on Communication, Control, and Computing

Series/Report Name or Number

2025 61st Allerton Conference on Communication, Control, and Computing Proceedings

ISSN

2836-4503

Type of Resource

Text

Genre of Resource

Conference Paper/Presentation

Language

eng

Handle URL

https://hdl.handle.net/2142/130290&&

Copyright and License Information

Copyright 2025 owned by the authors.

Owning Collections