Game-Theoretic Gradient Control for Robust Neural Network Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zaitseva, Maria, Tomilov, Ivan, Gusarova, Natalia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918104296062976
author Zaitseva, Maria
Tomilov, Ivan
Gusarova, Natalia
author_facet Zaitseva, Maria
Tomilov, Ivan
Gusarova, Natalia
contents Feed-forward neural networks (FFNNs) are vulnerable to input noise, reducing prediction performance. Existing regularization methods like dropout often alter network architecture or overlook neuron interactions. This study aims to enhance FFNN noise robustness by modifying backpropagation, interpreted as a multi-agent game, and exploring controlled target variable noising. Our "gradient dropout" selectively nullifies hidden layer neuron gradients with probability 1 - p during backpropagation, while keeping forward passes active. This is framed within compositional game theory. Additionally, target variables were perturbed with white noise or stable distributions. Experiments on ten diverse tabular datasets show varying impacts: improvement or diminishing of robustness and accuracy, depending on dataset and hyperparameters. Notably, on regression tasks, gradient dropout (p = 0.9) combined with stable distribution target noising significantly increased input noise robustness, evidenced by flatter MSE curves and more stable SMAPE values. These results highlight the method's potential, underscore the critical role of adaptive parameter tuning, and open new avenues for analyzing neural networks as complex adaptive systems exhibiting emergent behavior within a game-theoretic framework.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19143
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Game-Theoretic Gradient Control for Robust Neural Network Training
Zaitseva, Maria
Tomilov, Ivan
Gusarova, Natalia
Neural and Evolutionary Computing
Machine Learning
68T07
I.2.6
Feed-forward neural networks (FFNNs) are vulnerable to input noise, reducing prediction performance. Existing regularization methods like dropout often alter network architecture or overlook neuron interactions. This study aims to enhance FFNN noise robustness by modifying backpropagation, interpreted as a multi-agent game, and exploring controlled target variable noising. Our "gradient dropout" selectively nullifies hidden layer neuron gradients with probability 1 - p during backpropagation, while keeping forward passes active. This is framed within compositional game theory. Additionally, target variables were perturbed with white noise or stable distributions. Experiments on ten diverse tabular datasets show varying impacts: improvement or diminishing of robustness and accuracy, depending on dataset and hyperparameters. Notably, on regression tasks, gradient dropout (p = 0.9) combined with stable distribution target noising significantly increased input noise robustness, evidenced by flatter MSE curves and more stable SMAPE values. These results highlight the method's potential, underscore the critical role of adaptive parameter tuning, and open new avenues for analyzing neural networks as complex adaptive systems exhibiting emergent behavior within a game-theoretic framework.
title Game-Theoretic Gradient Control for Robust Neural Network Training
topic Neural and Evolutionary Computing
Machine Learning
68T07
I.2.6
url https://arxiv.org/abs/2507.19143