paper-with-me

Papers

Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression

2023-06-14 · Shahar Stein Ioushua, Inbar Hasidim, Ofer Shayevitz, Meir Feder

Learning algorithms that divide the data into batches are prevalent in many machine-learning applications, typically offering useful trade-offs between computational efficiency and performance. In this paper, we examine the benefits of batch-partitioning through the lens of a minimum-norm overparametrized linear regression model with isotropic Gaussian features. We suggest a natural small-batch version of the minimum-norm estimator and derive bounds on its quadratic risk. We then characterize the optimal batch size and show it is inversely proportional to the noise level, as well as to the overparametrization ratio. In contrast to minimum-norm, our estimator admits a stable risk behavior that is monotonically increasing in the overparametrization ratio, eliminating both the blowup at the interpolation point and the double-descent phenomenon. We further show that shrinking the batch minimum-norm estimator by a factor equal to the Weiner coefficient further stabilizes it and results in lower quadratic risk in all settings. Interestingly, we observe that the implicit regularization offered by the batch partition is partially explained by feature overlap between the batches. Our bound is derived via a novel combination of techniques, in particular normal approximation in the Wasserstein metric of noisy projections over random subspaces.

📄 PDF Abstract BibTeX arXiv:2306.08432

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiencyregression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization

2017-03-01 · NeurIPS 2017 12 · Tomoya Murata, Taiji Suzuki

In this paper, we develop a new accelerated stochastic gradient method for efficiently solving the convex regularized empirical risk minimization problem in mini-batch settings. The use of mini-batches is becoming a gold…

Risk of the Least Squares Minimum Norm Estimator under the Spike Covariance Model

2019-12-31 · Yasaman Mahdaviyeh, Zacharie Naulet

We study risk of the minimum norm linear least squares estimator in when the number of parameters $d$ depends on $n$, and $\frac{d}{n} \rightarrow \infty$. We assume that data has an underlying low rank structure by rest…

Interpolating Predictors in High-Dimensional Factor Regression

2020-02-06 · Florentina Bunea, Seth Strimas-Mackey, Marten Wegkamp

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 feat…

regressionVocal Bursts Intensity Prediction

On the robustness of minimum norm interpolators and regularized empirical risk minimizers

2020-12-01 · Geoffrey Chinot, Matthias Löffler, Sara van de Geer

This article develops a general theory for minimum norm interpolating estimators and regularized empirical risk minimizers (RERM) in linear models in the presence of additive, potentially adversarial, errors. In particul…

Minimum $\ell_{1}$-norm interpolators: Precise asymptotics and multiple descent

2021-10-18 · Yue Li, Yuting Wei

An evolving line of machine learning works observe empirical evidence that suggests interpolating estimators -- the ones that achieve zero training error -- may not necessarily be harmful. This paper pursues theoretical …