When Does More Regularization Imply Fewer Degrees of Freedom? Sufficient Conditions and Counter Examples from Lasso and Ridge Regression
Regularization aims to improve prediction performance of a given statistical modeling approach by moving to a second approach which achieves worse training error but is expected to have fewer degrees of freedom, i.e., better agreement between training and prediction error. We show here, however, that this expected behavior does not hold in general. In fact, counter examples are given that show regularization can increase the degrees of freedom in simple situations, including lasso and ridge regression, which are the most common regularization approaches in use. In such situations, the regularization increases both training error and degrees of freedom, and is thus inherently without merit. On the other hand, two important regularization scenarios are described where the expected reduction in degrees of freedom is indeed guaranteed: (a) all symmetric linear smoothers, and (b) linear regression versus convex constrained linear regression (as in the constrained variant of ridge regression and lasso).
Code (0)
등록된 구현이 없습니다.
Tasks
regressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FQGA-single: Towards Fewer Training Epochs and Fewer Model Parameters for Image-to-Image Translation Tasks
CycleGAN was trained on SynthRAD Grand Challenge Dataset using the single-epoch modification (SEM) method proposed in this paper which is referred to as (CycleGAN-single) compared to the usual method of training CycleGAN…
Computed Tomography (CT)Image-to-Image TranslationSSIMTranslationRethinking ValueDice: Does It Really Improve Performance?
Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvements: it beats the classical approach Behav…
Imitation LearningRethinking ValueDice: Does It Really Improve Performance?
Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvements: it beats the classical approach Behav…
Imitation LearningMemory Bounded Deep Convolutional Networks
In this work, we investigate the use of sparsity-inducing regularizers during training of Convolution Neural Networks (CNNs). These regularizers encourage that fewer connections in the convolution and fully connected lay…
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this wor…
Learning TheoryVocal Bursts Valence Prediction