The Gauss Markov theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. The classical approach to designing non-linear MVUEs is through maximum likelihood estimation (MLE) which often involves computationally challenging optimizations. On the other hand, deep learning methods allow for non-linear estimators with fixed computational complexity. Learning based estimators perform optimally on average with respect to their training set but may suffer from significant bias in other parameters. To avoid this, we propose to add a simple bias constraint to the loss function, resulting in an estimator we refer to as Bias Constrained Estimator (BCE). We prove that this yields asymptotic MVUEs that behave similarly to the classical MLEs and asymptotically attain the Cramer Rao bound. We demonstrate the advantages of our approach in the context of signal to noise ratio estimation as well as covariance estimation. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance. Examples include distributed sensor networks and data augmentation in test-time. In such applications, we show that BCE leads to asymptotically consistent estimators.
Testing approximate normality of an estimator using the estimated MSE and bias with an application to the shape parameter of the generalized Pareto distribution
MAUNet-Light: A Concise MAUNet Architecture for Bias Correction and Downscaling of Precipitation Estimates
Department of Artificial Intelligence, Indian Institute of Technology Kharagpur(人工智能系,印度理工学院科丁格浦分校);Sustainability and Data Sciences Laboratory (SDS Lab), Civil and Environmental Engineering, Northeastern University(可持续性与数据科学实验室(SDS实验室),土木与环境工程,东北大学);AI for Climate and Sustainability (AI4CaS), The Institute for Experiential AI (IEAI), Northeastern University(人工智能用于气候与可持续性(AI4CaS),体验式人工智能研究所(IEAI),东北大学)
No evaluation without fair representation : Impact of label and selection bias on the evaluation, performance and mitigation of classification models
Université catholique de Louvain(比利时列日天主大学);Institute of Information and Communication Technologies, Electronics and Applied Mathematics(信息与通信技术、电子与应用数学研究所);Universiteit Antwerpen(安特卫普大学);Adrem Data Lab(Adrem数据实验室);Louvain Research Institute in Management and Organizations(列日管理与组织研究 institute)
Biases in Inverse Ising Estimates of Near-Critical Behaviour
University of Bristol(布里斯托大学);Kyoto Institute of Technology(京都工艺纤维大学);ESPCI Paris(巴黎高等物理化工学院);Université PSL(巴黎文理研究大学);State University of New York at Buffalo(纽约州立大学布法罗分校)
本文以 SK 模型为基准揭示逆 Ising 推断中 PLM 等估计器在近临界区的小样本偏差,并提出数据驱动校正方法用于 fMRI 数据,警示真实数据集的临界性归因需谨慎。
Leveraging Deep Learning for Physical Model Bias of Global Air Quality Estimates
Department of Computer Science(计算机科学系);NASA Jet Propulsion Lab(美国国家航空航天局喷气推进实验室);University of Oxford(牛津大学);Jet Propulsion Laboratory(喷气推进实验室);California Institute of Technology(加州理工学院);OATML