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

arXiv: https://arxiv.org/abs/2008.07281 · HTML: https://mlsanity.com/paper/2008.07281/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 30 of 33)

- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024)
- [A Comprehensive Survey of Regression Based Loss Functions for Time Series Forecasting](https://mlsanity.com/paper/2211.02989/) (2022)
- [Theoretical Error Performance Analysis for Variational Quantum Circuit Based Functional Regression](https://mlsanity.com/paper/2206.04804/) (2022)
- [Exploring Active 3D Object Detection from a Generalization Perspective](https://mlsanity.com/paper/2301.09249/) (2023)
- [Improving evidential deep learning via multi-task learning](https://mlsanity.com/paper/2112.09368/) (2021)
- [Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing](https://mlsanity.com/paper/2203.06031/) (2022)
- [A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models](https://mlsanity.com/paper/2306.00331/) (2023)
- [ECHOPulse: ECG controlled echocardio-grams video generation](https://mlsanity.com/paper/2410.03143/) (2024)
- [Mirror Online Conformal Prediction with Intermittent Feedback](https://mlsanity.com/paper/2503.10345/) (2025)
- [Online Capacity Scaling Augmented With Unreliable Machine Learning Predictions](https://mlsanity.com/paper/2101.12160/) (2021)
- [Comparison of two artificial neural networks trained for the surrogate modeling of stress in materially heterogeneous elastoplastic solids](https://mlsanity.com/paper/2210.16994/) (2022)
- [Neural Regression For Scale-Varying Targets](https://mlsanity.com/paper/2211.07447/) (2022)
- [Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitz](https://mlsanity.com/paper/2305.07618/) (2023)
- [Quantum Machine Learning: An Interplay Between Quantum Computing and Machine Learning](https://mlsanity.com/paper/2411.09403/) (2024)
- [Symbolic Regression via Neural Networks](https://mlsanity.com/paper/2605.04337/) (2026)
- [Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition](https://mlsanity.com/paper/2201.10609/) (2022)
- [Evaluating the Impact of Loss Function Variation in Deep Learning for Classification](https://mlsanity.com/paper/2210.16003/) (2022)
- [Multi-Channel Hypergraph Contrastive Learning for Matrix Completion](https://mlsanity.com/paper/2411.01376/) (2024)
- [RadarNeXt: Real-Time and Reliable 3D Object Detector Based On 4D mmWave Imaging Radar](https://mlsanity.com/paper/2501.02314/) (2025)
- [On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion](https://mlsanity.com/paper/2111.14220/) (2021)
- [Inference and Denoise: Causal Inference-based Neural Speech Enhancement](https://mlsanity.com/paper/2211.01189/) (2022)
- [Open-CRB: Towards Open World Active Learning for 3D Object Detection](https://mlsanity.com/paper/2310.10391/) (2023)
- [Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks](https://mlsanity.com/paper/2311.12356/) (2023)
- [Optimizing CO2 Capture in Pressure Swing Adsorption Units: A Deep Neural Network Approach with Optimality Evaluation and Operating Maps for Decision-Making](https://mlsanity.com/paper/2312.03873/) (2023)
- [From 2015 to 2023: How Machine Learning Aids Natural Product Analysis](https://mlsanity.com/paper/2408.00793/) (2024)
- [EUR-USD Exchange Rate Forecasting Based on Information Fusion with Large Language Models and Deep Learning Methods](https://mlsanity.com/paper/2408.13214/) (2024)
- [A multi-source data power load forecasting method using attention mechanism-based parallel cnn-gru](https://mlsanity.com/paper/2409.17889/) (2024)
- [QCResUNet: Joint Subject-level and Voxel-level Segmentation Quality Prediction](https://mlsanity.com/paper/2412.07156/) (2024)
- [Learning Aerodynamics for the Control of Flying Humanoid Robots](https://mlsanity.com/paper/2506.00305/) (2025)
- [ToonOut: Fine-tuned Background-Removal for Anime Characters](https://mlsanity.com/paper/2509.06839/) (2025)

## 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.