2017/09/11 by Taesup Moon, Moon, Taesup
Computer Science · Engineering · Mathematics · #FOS: Computer and information sciences #Image and Signal Denoising Methods #Information Theory (cs.IT) #Machine Learning (cs.LG) #Neural Networks and Applications #Sparse and Compressive Sensing Techniques #Ultrasonics and Acoustic Wave Propagation #cs.IT #cs.LG #math.IT
paper · pdf · doi:10.48550/arxiv.1709.03657
submitted to ICML 2018
openalex publication_date 2017/09/11 · arxiv created 2018/02/24 · arxiv updated 2018/02/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We obtain a denoising loss bound of the recently proposed neural network based universal discrete denoiser, Neural DUDE, which can adaptively learn its parameters solely from the noise-corrupted data, by minimizing the empirical estimated loss. The resulting bound resembles the generalization error bound of the standard empirical risk minimizers (ERM) in supervised learning, and we show that the well-known bias-variance tradeoff also exists in our loss bound. The key tool we develop is the concentration of the unbiased estimated loss on the true denoising loss, which is shown to hold uniformly for all bounded network parameters and all underlying clean sequences. For proving our main results, we make a novel application of the tools from the statistical learning theory. Finally, we show that the hyperparameters of Neural DUDE can be chosen from a small validation set to significantly improve the denoising performance, as predicted by the theoretical result of this paper.