An Analysis of Minimum Error Entropy Loss Functions in Wireless Communications

TL;DR

This paper presents the minimum error entropy (MEE) loss function for deep learning in wireless communications, demonstrating its robustness and improved performance over traditional loss functions in noisy and fading environments.

Contribution

It introduces a computationally efficient MEE criterion tailored for wireless applications and validates its superiority through simulations in over-the-air regression and indoor localization.

Findings

MEE outperforms MSE and MAE in accuracy and convergence speed.

Achieves over 20% performance improvement in simulations.

Enhances robustness in noisy wireless scenarios.

Abstract

This paper introduces the minimum error entropy (MEE) criterion as an advanced information-theoretic loss function tailored for deep learning applications in wireless communications. The MEE criterion leverages higher-order statistical properties, offering robustness in noisy scenarios like Rayleigh fading and impulsive interference. In addition, we propose a less computationally complex version of the MEE function to enhance practical usability in wireless communications. The method is evaluated through simulations on two critical applications: over-the-air regression and indoor localization. Results indicate that the MEE criterion outperforms conventional loss functions, such as mean squared error (MSE) and mean absolute error (MAE), achieving significant performance improvements in terms of accuracy, over $20 \%$ gain over traditional methods, and convergence speed across various channel conditions. This work establishes MEE as a promising alternative for wireless communication tasks in deep learning models, enabling better resilience and adaptability.