English
Related papers

Related papers: Analysis of Interpolating Regression Models and th…

200 papers

Overparameterization in deep learning typically refers to settings where a trained neural network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do not. In the case of…

Machine Learning · Computer Science 2023-03-24 Edo Cohen-Karlik , Itamar Menuhin-Gruman , Raja Giryes , Nadav Cohen , Amir Globerson

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

Regularized linear regression is a promising approach for binary classification problems in which the training set has noisy labels since the regularization term can help to avoid interpolating the mislabeled data points. In this paper we…

Machine Learning · Computer Science 2023-11-07 Danil Akhtiamov , Reza Ghane , Babak Hassibi

The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal solutions to non-convex optimization problems, and despite…

Statistics Theory · Mathematics 2021-03-17 Peter L. Bartlett , Andrea Montanari , Alexander Rakhlin

This work studies finite-sample properties of the risk of the minimum-norm interpolating predictor in high-dimensional regression models. If the effective rank of the covariance matrix $\Sigma$ of the $p$ regression features is much larger…

Machine Learning · Statistics 2021-03-23 Florentina Bunea , Seth Strimas-Mackey , Marten Wegkamp

We consider fully row/column-correlated linear regression models and study several classical estimators (including minimum norm interpolators (GLS), ordinary least squares (LS), and ridge regressors). We show that \emph{Random Duality…

Machine Learning · Statistics 2024-06-14 Mihailo Stojnic

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

In this paper, we provide a precise characterization of generalization properties of high dimensional kernel ridge regression across the under- and over-parameterized regimes, depending on whether the number of training data n exceeds the…

Machine Learning · Statistics 2021-02-25 Fanghui Liu , Zhenyu Liao , Johan A. K. Suykens

We consider the linear model $\mathbf{y} = \mathbf{X} \mathbf{\beta}_\star + \mathbf{\epsilon}$ with $\mathbf{X}\in \mathbb{R}^{n\times p}$ in the overparameterized regime $p>n$. We estimate $\mathbf{\beta}_\star$ via generalized (weighted)…

Machine Learning · Statistics 2020-11-04 Denny Wu , Ji Xu

Overparametrized neural networks tend to perfectly fit noisy training data yet generalize well on test data. Inspired by this empirical observation, recent work has sought to understand this phenomenon of benign overfitting or harmless…

Machine Learning · Statistics 2022-02-23 Andrew D. McRae , Santhosh Karnik , Mark A. Davenport , Vidya Muthukumar

We study the overfitting behavior of fully connected deep Neural Networks (NNs) with binary weights fitted to perfectly classify a noisy training set. We consider interpolation using both the smallest NN (having the minimal number of…

Machine Learning · Computer Science 2024-10-28 Itamar Harel , William M. Hoza , Gal Vardi , Itay Evron , Nathan Srebro , Daniel Soudry

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

A surprising phenomenon in modern machine learning is the ability of a highly overparameterized model to generalize well (small error on the test data) even when it is trained to memorize the training data (zero error on the training data).…

Machine Learning · Statistics 2022-12-01 Jasper Tan , Blake Mason , Hamid Javadi , Richard G. Baraniuk

We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never observed in the training input. This mechanism induces a novel bottleneck absent from dense…

Machine Learning · Statistics 2026-05-25 John Sous , Michael Winer

We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to…

Machine Learning · Statistics 2025-12-12 Gabriel Clara , Yazan Mash'al

Increasing the size of overparameterized neural networks has been a key in achieving state-of-the-art performance. This is captured by the double descent phenomenon, where the test loss follows a decreasing-increasing-decreasing pattern (or…

Machine Learning · Computer Science 2024-05-09 Yihao Xue , Kyle Whitecross , Baharan Mirzasoleiman

For classification, the problem of class imbalance is well known and has been extensively studied. In this paper, we argue that imbalance in regression is an equally important problem which has so far been overlooked: Due to under- and…

Machine Learning · Computer Science 2024-02-20 Daniel Kowatsch , Nicolas M. Müller , Kilian Tscharke , Philip Sperl , Konstantin Bötinger

We study the robust interpolation problem of arbitrary data distributions supported on a bounded space and propose a two-fold law of robustness. Robust interpolation refers to the problem of interpolating $n$ noisy training data points in…

Machine Learning · Computer Science 2023-06-02 Yihan Wu , Heng Huang , Hongyang Zhang

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Overfitting in linear regression is broken down into two main causes. First, the formula for the estimator includes 'forbidden knowledge' about training observations' residuals, and it loses this advantage when deployed out-of-sample.…

Methodology · Statistics 2022-09-27 Chris Rohlfs