paper-with-me

홈 › Papers

Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond

2023-01-31 · Meyer Scetbon, Elvis Dohmatob

In this work we study the robustness to adversarial attacks, of early-stopping strategies on gradient-descent (GD) methods for linear regression. More precisely, we show that early-stopped GD is optimally robust (up to an absolute constant) against Euclidean-norm adversarial attacks. However, we show that this strategy can be arbitrarily sub-optimal in the case of general Mahalanobis attacks. This observation is compatible with recent findings in the case of classification~\cite{Vardi2022GradientMP} that show that GD provably converges to non-robust models. To alleviate this issue, we propose to apply instead a GD scheme on a transformation of the data adapted to the attack. This data transformation amounts to apply feature-depending learning rates and we show that this modified GD is able to handle any Mahalanobis attack, as well as more general attacks under some conditions. Unfortunately, choosing such adapted transformations can be hard for general attacks. To the rescue, we design a simple and tractable estimator whose adversarial risk is optimal up to within a multiplicative constant of 1.1124 in the population regime, and works for any norm.

📄 PDF Abstract BibTeX arXiv:2301.13486

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Implicit Sparse Regularization: The Impact of Depth and Early Stopping

2021-08-12 · NeurIPS 2021 12 · Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde, Raymond K. W. Wong

In this paper, we study the implicit bias of gradient descent for sparse regression. We extend results on regression with quadratic parametrization, which amounts to depth-2 diagonal linear networks, to more general dept…

regression

Fast Robust Kernel Regression through Sign Gradient Descent with Early Stopping

2023-06-29 · Oskar Allerbo

Kernel ridge regression, KRR, is a generalization of linear ridge regression that is non-linear in the data, but linear in the model parameters. Here, we introduce an equivalent formulation of the objective function of K…

regression

On Regularization via Early Stopping for Least Squares Regression

2024-06-06 · Rishi Sonthalia, Jackie Lok, Elizaveta Rebrova

A fundamental problem in machine learning is understanding the effect of early stopping on the parameters obtained and the generalization capabilities of the model. Even for linear models, the effect is not fully underst…

regression

The Implicit Regularization of Momentum Gradient Descent with Early Stopping

2022-01-14 · Li Wang, Yingcong Zhou, Zhiguo Fu

The study on the implicit regularization induced by gradient-based optimization is a longstanding pursuit. In the present paper, we characterize the implicit regularization of momentum gradient descent (MGD) with early s…

regression

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression

2025-02-18 · Jingfeng Wu, Peter Bartlett, Matus Telgarsky, Bin Yu

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work i…

regression