English
Related papers

Related papers: Minimum $\ell_{1}$-norm interpolators: Precise asy…

200 papers

Understanding when and why interpolating methods generalize well has recently been a topic of interest in statistical learning theory. However, systematically connecting interpolating methods to achievable notions of optimality has only…

Machine Learning · Statistics 2021-10-22 Eduard Oravkin , Patrick Rebeschini

Interpolators are unstable. For example, the mininum $\ell_2$ norm least square interpolator exhibits unbounded test errors when dealing with noisy data. In this paper, we study how ensemble stabilizes and thus improves the generalization…

Machine Learning · Statistics 2023-09-08 Mingqi Wu , Qiang Sun

We consider an underdetermined noisy linear regression model where the minimum-norm interpolating predictor is known to be consistent, and ask: can uniform convergence in a norm ball, or at least (following Nagarajan and Kolter) the subset…

Machine Learning · Statistics 2021-01-15 Lijia Zhou , Danica J. Sutherland , Nathan Srebro

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

We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number of data points and parameters tends to infinity when a weight…

Machine Learning · Statistics 2023-11-13 Jiyoung Park , Ian Pelakh , Stephan Wojtowytsch

In compressed sensing, in order to recover a sparse or nearly sparse vector from possibly noisy measurements, the most popular approach is $\ell_1$-norm minimization. Upper bounds for the $\ell_2$- norm of the error between the true and…

Machine Learning · Statistics 2015-12-31 M. Eren Ahsen , M. Vidyasagar

Good generalization performance on high-dimensional data crucially hinges on a simple structure of the ground truth and a corresponding strong inductive bias of the estimator. Even though this intuition is valid for regularized models, in…

Machine Learning · Statistics 2022-10-28 Konstantin Donhauser , Nicolo Ruggeri , Stefan Stojanovic , Fanny Yang

Functions of interest are often smooth and sparse in some sense, and both priors should be taken into account when interpolating sampled data. Classical linear interpolation methods are effective under strong regularity assumptions, but…

Functional Analysis · Mathematics 2015-03-27 Holger Rauhut , Rachel Ward

We establish exact asymptotic expressions for the normalized mutual information and minimum mean-square-error (MMSE) of sparse linear regression in the sub-linear sparsity regime. Our result is achieved by a generalization of the adaptive…

Information Theory · Computer Science 2023-04-11 Lan V. Truong

We bound the excess risk of interpolating deep linear networks trained using gradient flow. In a setting previously used to establish risk bounds for the minimum $\ell_2$-norm interpolant, we show that randomly initialized deep linear…

Machine Learning · Computer Science 2023-02-08 Niladri S. Chatterji , Philip M. Long

In some studies \citep[e.g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero. Despite numerous works towards…

Machine Learning · Statistics 2022-02-25 Yue Xing , Qifan Song , Guang Cheng

We consider the empirical risk minimization problem for linear supervised learning, with regularization by structured sparsity-inducing norms. These are defined as sums of Euclidean norms on certain subsets of variables, extending the usual…

Machine Learning · Statistics 2011-11-23 Rodolphe Jenatton , Jean-Yves Audibert , Francis Bach

Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of linear regression a…

Machine Learning · Computer Science 2024-08-28 Neil Mallinar , Austin Zane , Spencer Frei , Bin Yu

This paper considers binary classification of high-dimensional features under a postulated model with a low-dimensional latent Gaussian mixture structure and non-vanishing noise. A generalized least squares estimator is used to estimate the…

Machine Learning · Statistics 2023-03-30 Xin Bing , Marten Wegkamp

Sparse estimation methods are aimed at using or obtaining parsimonious representations of data or models. While naturally cast as a combinatorial optimization problem, variable or feature selection admits a convex relaxation through the…

Machine Learning · Computer Science 2012-04-23 Francis Bach , Rodolphe Jenatton , Julien Mairal , Guillaume Obozinski

We study the learning properties of nonparametric ridge-less least squares. In particular, we consider the common case of estimators defined by scale dependent kernels, and focus on the role of the scale. These estimators interpolate the…

Machine Learning · Statistics 2021-11-11 Nicolò Pagliana , Alessandro Rudi , Ernesto De Vito , Lorenzo Rosasco

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles:…

Machine Learning · Statistics 2021-09-16 Ke Wang , Christos Thrampoulidis

Most modern learning problems are over-parameterized, where the number of learnable parameters is much greater than the number of training data points. In this over-parameterized regime, the training loss typically has infinitely many…

Machine Learning · Computer Science 2025-06-23 Kanumuri Nithin Varma , Babak Hassibi

Popular iterative algorithms such as boosting methods and coordinate descent on linear models converge to the maximum $\ell_1$-margin classifier, a.k.a. sparse hard-margin SVM, in high dimensional regimes where the data is linearly…

Machine Learning · Statistics 2023-01-23 Stefan Stojanovic , Konstantin Donhauser , Fanny Yang

We prove that the Minimum Description Length learning rule exhibits tempered overfitting. We obtain tempered agnostic finite sample learning guarantees and characterize the asymptotic behavior in the presence of random label noise.

Machine Learning · Computer Science 2023-02-15 Naren Sarayu Manoj , Nathan Srebro