In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expected feature vectors is upper bounded by the sum of an approximation error, an estimation error, and an optimization error. Leveraging upon error decomposition techniques in statistical learning theory and non-convex optimization theory, we derive upper bounds for each of the three aforementioned errors and impose necessary constraints on DNN models. Moreover, we assess our theoretical results through a set of image de-noising and speech enhancement experiments. Our proposed upper bounds of MAE for DNN based vector-to-vector regression are corroborated by the experimental results and the upper bounds are valid with and without the 'over-parametrization' technique.
Qi J., Du J., Siniscalchi S.M., Ma X., Lee C.-H. (2020). Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network-Based Vector-to-Vector Regression. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 68, 3411-3422 [10.1109/TSP.2020.2993164].
Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network-Based Vector-to-Vector Regression
Siniscalchi S. M.Supervision
;
2020-05-01
Abstract
In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expected feature vectors is upper bounded by the sum of an approximation error, an estimation error, and an optimization error. Leveraging upon error decomposition techniques in statistical learning theory and non-convex optimization theory, we derive upper bounds for each of the three aforementioned errors and impose necessary constraints on DNN models. Moreover, we assess our theoretical results through a set of image de-noising and speech enhancement experiments. Our proposed upper bounds of MAE for DNN based vector-to-vector regression are corroborated by the experimental results and the upper bounds are valid with and without the 'over-parametrization' technique.File | Dimensione | Formato | |
---|---|---|---|
Analyzing_Upper_Bounds_on_Mean_Absolute_Errors_for_Deep_Neural_Network-Based_Vector-to-Vector_Regression.pdf
Solo gestori archvio
Descrizione: main document
Tipologia:
Versione Editoriale
Dimensione
728.19 kB
Formato
Adobe PDF
|
728.19 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
2008.05459v1.pdf
accesso aperto
Tipologia:
Pre-print
Dimensione
5.83 MB
Formato
Adobe PDF
|
5.83 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.