Linear regression with overparameterized linear neural networks: Tight upper and lower bounds for implicit $\ell^1$-regularization
Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has studied diagonal linear neural networks in the regression setting. These studies have shown that, when initialized with small weights, gradient descent tends to favor solutions with minimal $\ell^1$-norm - an effect known as implicit regularization. In this paper, we investigate implicit regularization in diagonal linear neural networks of depth $D\ge 2$ for overparameterized linear regression problems. We focus on analyzing the approximation error between the limit point of gradient flow trajectories and the solution to the $\ell^1$-minimization problem. By deriving tight upper and lower bounds on the approximation error, we precisely characterize how the approximation error depends on the scale of initialization $\alpha$. Our results reveal a qualitative difference between depths: for $D \ge 3$, the error decreases linearly with $\alpha$, whereas for $D=2$, it decreases at rate $\alpha^{1-\varrho}$, where the parameter $\varrho \in [0,1)$ can be explicitly characterized. Interestingly, this parameter is closely linked to so-called null space property constants studied in the sparse recovery literature. We demonstrate the asymptotic tightness of our bounds through explicit examples. Numerical experiments corroborate our theoretical findings and suggest that deeper networks, i.e., $D \ge 3$, may lead to better generalization, particularly for realistic initialization scales.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Local SGD in Overparameterized Linear Regression
We consider distributed learning using constant stepsize SGD (DSGD) over several devices, each sending a final model update to a central server. In a final step, the local estimates are aggregated. We prove in the settin…
regressionLast Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
Stochastic gradient descent (SGD) has been shown to generalize well in many deep learning applications. In practice, one often runs SGD with a geometrically decaying stepsize, i.e., a constant initial stepsize followed b…
regressionTheoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
Meta-learning has arisen as a successful method for improving training performance by training over many similar tasks, especially with deep neural networks (DNNs). However, the theoretical understanding of when and why …
DiversityMeta-LearningregressionRisk Bounds of Accelerated SGD for Overparameterized Linear Regression
Accelerated stochastic gradient descent (ASGD) is a workhorse in deep learning and often achieves better generalization performance than SGD. However, existing optimization theory can only explain the faster convergence …
regressionOverfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
Recently, there have been significant interests in studying the so-called "double-descent" of the generalization error of linear regression models under the overparameterized and overfitting regime, with the hope that su…
compressed sensingregression