2025/08/04 by Gutierrez, Roman, Tang, Tony Kai, Gutierrez, Isabel
#62F35 #62J02 #65D10 #68T07 #68T30 #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #G.1.2 #G.3 #I.2.6 #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · doi:10.48550/arxiv.2508.02874
Robust regression techniques rely on least-squares optimization, which works well for Gaussian noise but fails in the presence of asymmetric structured noise. We propose a hybrid neural-symbolic architecture where a transformer encoder processes numerical sequences, a compression NN predicts symbolic parameters, and a fixed symbolic equation reconstructs the original sequence. Using synthetic data, the training objective is to recover the original sequence after adding asymmetric structured noise, effectively learning a symbolic fit guided by neural parameter estimation. Our model achieves a median regression MSE of 6e-6 to 3.5e-5 on synthetic wearable data, which is a 10-300 times improvement when compared with ordinary least squares fit and robust regression techniques such as Huber loss or SoftL1.