mlsanityData to 7 Oct 2026

On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression

arXiv 2008.07281 ↗First posted 12 Aug 2020eess.AS cs.LG cs.SDcited by 33

Not on the map. Why?

Abstract (arXiv)

In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression. The goal of this work is two-fold: (i) presenting performance bounds of MAE, and (ii) demonstrating new properties of MAE that make it more appropriate than mean squared error (MSE) as a loss function for DNN based vector-to-vector regression. First, we show that a generalized upper-bound for DNN-based vector- to-vector regression can be ensured by leveraging the known Lipschitz continuity property of MAE. Next, we derive a new generalized upper bound in the presence of additive noise. Finally, in contrast to conventional MSE commonly adopted to approximate Gaussian errors for regression, we show that MAE can be interpreted as an error modeled by Laplacian distribution. Speech enhancement experiments are conducted to corroborate our proposed theorems and validate the performance advantages of MAE over MSE for DNN based regression.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 8; 2023: 6; 2024: 8; 2025: 4; 2026: 4.

33 papers.

Sort:

By area:

  1. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  2. 2022A Comprehensive Survey of Regression Based Loss Functions for Time Series Forecastingcited by 33
  3. 2022Theoretical Error Performance Analysis for Variational Quantum Circuit Based Functional Regressioncited by 26
  4. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  5. 2021Improving evidential deep learning via multi-task learningcited by 13
  6. 2022Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processingcited by 10
  7. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 9
  8. 2024ECHOPulse: ECG controlled echocardio-grams video generationcited by 8
  9. 2025Mirror Online Conformal Prediction with Intermittent Feedbackcited by 6
  10. 2021Online Capacity Scaling Augmented With Unreliable Machine Learning Predictionscited by 3
  11. 2022Comparison of two artificial neural networks trained for the surrogate modeling of stress in materially heterogeneous elastoplastic solidscited by 3
  12. 2022Neural Regression For Scale-Varying Targetscited by 2
21 more
  1. 2023Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitzcited by 2
  2. 2024Quantum Machine Learning: An Interplay Between Quantum Computing and Machine Learningcited by 2
  3. 2026Symbolic Regression via Neural Networkscited by 2
  4. 2022Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognitioncited by 1
  5. 2022Evaluating the Impact of Loss Function Variation in Deep Learning for Classificationcited by 1
  6. 2024Multi-Channel Hypergraph Contrastive Learning for Matrix Completioncited by 1
  7. 2025RadarNeXt: Real-Time and Reliable 3D Object Detector Based On 4D mmWave Imaging Radarcited by 1
  8. 2021On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversioncited by 0
  9. 2022Inference and Denoise: Causal Inference-based Neural Speech Enhancementcited by 0
  10. 2023Open-CRB: Towards Open World Active Learning for 3D Object Detectioncited by 0
  11. 2023Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networkscited by 0
  12. 2023Optimizing CO2 Capture in Pressure Swing Adsorption Units: A Deep Neural Network Approach with Optimality Evaluation and Operating Maps for Decision-Makingcited by 0
  13. 2024From 2015 to 2023: How Machine Learning Aids Natural Product Analysiscited by 0
  14. 2024EUR-USD Exchange Rate Forecasting Based on Information Fusion with Large Language Models and Deep Learning Methodscited by 0
  15. 2024A multi-source data power load forecasting method using attention mechanism-based parallel cnn-grucited by 0
  16. 2024QCResUNet: Joint Subject-level and Voxel-level Segmentation Quality Predictioncited by 0
  17. 2025Learning Aerodynamics for the Control of Flying Humanoid Robotscited by 0
  18. 2025ToonOut: Fine-tuned Background-Removal for Anime Characterscited by 0
  19. 2026Logit Distance Bounds Representational Similaritycited by 0
  20. 2026Alternate loss functions and regression models that achieve robustness to outliers by modulating the learning ratecited by 0
  21. 2026About the Influence of Workflow Topology on Task Intensity Prediction through Graph Learningcited by 0