English
Related papers

Related papers: Interpolation can hurt robust generalization even …

200 papers

Generalization is one of the fundamental issues in machine learning. However, traditional techniques like uniform convergence may be unable to explain generalization under overparameterization. As alternative approaches, techniques based on…

Machine Learning · Computer Science 2022-03-22 Jiaye Teng , Jianhao Ma , Yang Yuan

We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-parameterized linear regression models using gradient descent with weight…

Machine Learning · Computer Science 2026-02-09 Mingyue Xu , Gal Vardi , Itay Safran

Design of reliable systems must guarantee stability against input perturbations. In machine learning, such guarantee entails preventing overfitting and ensuring robustness of models against corruption of input data. In order to maximize…

Machine Learning · Statistics 2019-08-08 Judy Hoffman , Daniel A. Roberts , Sho Yaida

Simultaneously addressing multiple objectives is becoming increasingly important in modern machine learning. At the same time, data is often high-dimensional and costly to label. For a single objective such as prediction risk, conventional…

Machine Learning · Statistics 2025-03-13 Tobias Wegel , Filip Kovačević , Alexandru Ţifrea , Fanny Yang

Interpolators -- estimators that achieve zero training error -- have attracted growing attention in machine learning, mainly because state-of-the art neural networks appear to be models of this type. In this paper, we study minimum $\ell_2$…

Statistics Theory · Mathematics 2022-09-12 Trevor Hastie , Andrea Montanari , Saharon Rosset , Ryan J. Tibshirani

Conventional regularization is designed to control variance, but in small-data regression it can also aggravate underfitting when predictive signal is concentrated in weak directions of a restricted representation. We study a…

Machine Learning · Computer Science 2026-04-21 Dongseok Kim , Gisung Oh

We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations. Our regularizer can be derived as a controlled approximation from first principles,…

Machine Learning · Statistics 2018-05-23 Kevin Roth , Aurelien Lucchi , Sebastian Nowozin , Thomas Hofmann

Weak-to-strong generalization, where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher, has been widely observed but the mechanisms that enable it have remained poorly understood.…

Machine Learning · Statistics 2025-05-27 Behrad Moniri , Hamed Hassani

We establish precise structural and risk equivalences between subsampling and ridge regularization for ensemble ridge estimators. Specifically, we prove that linear and quadratic functionals of subsample ridge estimators, when fitted with…

Statistics Theory · Mathematics 2023-10-19 Pratik Patil , Jin-Hong Du

Despite perfectly interpolating the training data, deep neural networks (DNNs) can often generalize fairly well, in part due to the "implicit regularization" induced by the learning algorithm. Nonetheless, various forms of regularization,…

Machine Learning · Computer Science 2022-02-23 Navid Azizan , Sahin Lale , Babak Hassibi

Induction benefits from useful priors. Penalized regression approaches, like ridge regression, shrink weights toward zero but zero association is usually not a sensible prior. Inspired by simple and robust decision heuristics humans use, we…

Machine Learning · Computer Science 2021-10-26 Sebastian Bobadilla-Suarez , Matt Jones , Bradley C. Love

Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To…

In high-dimensional data analysis, regularization methods pursuing sparsity and/or low rank have received a lot of attention recently. To provide a proper amount of shrinkage, it is typical to use a grid search and a model comparison…

Methodology · Statistics 2019-01-01 Yiyuan She , Hoang Tran

Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks. While it has been empirically observed that flatness measures consistently correlate strongly…

Machine Learning · Computer Science 2021-11-05 Henning Petzka , Michael Kamp , Linara Adilova , Cristian Sminchisescu , Mario Boley

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK) are provably sub-optimal and benign overfitting does not…

Machine Learning · Computer Science 2024-06-12 Dan Qiao , Kaiqi Zhang , Esha Singh , Daniel Soudry , Yu-Xiang Wang

Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve…

Machine Learning · Computer Science 2018-05-28 Dániel Varga , Adrián Csiszárik , Zsolt Zombori

Features in predictive models are not exchangeable, yet common supervised models treat them as such. Here we study ridge regression when the analyst can partition the features into $K$ groups based on external side-information. For example,…

Methodology · Statistics 2021-03-05 Nikolaos Ignatiadis , Panagiotis Lolas

In this study, we explore the effects of including noise predictors and noise observations when fitting linear regression models. We present empirical and theoretical results that show that double descent occurs in both cases, albeit with…

Statistics Theory · Mathematics 2024-08-16 Insha Ullah , A. H. Welsh

We analyse the interpolator with minimal $\ell_2$-norm $\hat{\beta}$ in a general high dimensional linear regression framework where $\mathbb Y=\mathbb X\beta^*+\xi$ where $\mathbb X$ is a random $n\times p$ matrix with independent…

Statistics Theory · Mathematics 2021-01-06 Geoffrey Chinot , Matthieu Lerasle