English
Related papers

Related papers: Classification vs regression in overparameterized …

200 papers

In deep learning it is common to overparameterize neural networks, that is, to use more parameters than training samples. Quite surprisingly training the neural network via (stochastic) gradient descent leads to models that generalize very…

Optimization and Control · Mathematics 2025-01-30 Hung-Hsu Chou , Johannes Maly , Holger Rauhut

We investigate the relation of two fundamental tools in machine learning and signal processing, that is the support vector machine (SVM) for classification, and the Lasso technique used in regression. We show that the resulting optimization…

Machine Learning · Computer Science 2014-04-28 Martin Jaggi

A formal link between regression and classification has been tenuous. Even though the margin maximization term $\|w\|$ is used in support vector regression, it has at best been justified as a regularizer. We show that a regression problem…

Machine Learning · Computer Science 2025-11-07 Jayadeva , Naman Dwivedi , Hari Krishnan , N. M. Anoop Krishnan

Semi-functional linear regression models postulate a linear relationship between a scalar response and a functional covariate, and also include a non-parametric component involving a univariate explanatory variable. It is of practical…

Methodology · Statistics 2023-08-08 Graciela Boente , Matias Salibian-Barrera , Pablo Vena

This paper investigates the asymptotic behavior of the soft-margin and hard-margin support vector machine (SVM) classifiers for simultaneously high-dimensional and numerous data (large $n$ and large $p$ with $n/p\to\delta$) drawn from a…

Information Theory · Computer Science 2020-03-31 Abla Kammoun , Mohamed-Slim Alouini

Statisticians often face the choice between using probability models or a paradigm defined by minimising a loss function. Both approaches are useful and, if the loss can be re-cast into a proper probability model, there are many tools to…

Methodology · Statistics 2022-03-29 Jack Jewson , David Rossell

This paper is motivated by an open problem around deep networks, namely, the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we analyze this phenomenon in…

Machine Learning · Computer Science 2019-08-28 Hrushikesh Mhaskar , Tomaso Poggio

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

Machine Learning · Statistics 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

The classical hinge-loss support vector machines (SVMs) model is sensitive to outlier observations due to the unboundedness of its loss function. To circumvent this issue, recent studies have focused on non-convex loss functions, such as…

Machine Learning · Computer Science 2022-07-19 Ítalo Santana , Breno Serrano , Maximilian Schiffer , Thibaut Vidal

One of the major open problems in machine learning is to characterize generalization in the overparameterized regime, where most traditional generalization bounds become inconsistent even for overparameterized linear regression. In many…

Machine Learning · Computer Science 2023-11-22 Jing Xu , Jiaye Teng , Yang Yuan , Andrew Chi-Chih Yao

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao

Identification in errors-in-variables regression models was recently extended to wide models classes by S. Schennach (Econometrica, 2007) (S) via use of generalized functions. In this paper the problems of non- and semi- parametric…

Methodology · Statistics 2009-09-30 Victoria Zinde-Walsh

Concerning bivariate least squares linear regression, the classical approach pursued for functional models in earlier attempts is reviewed using a new formalism in terms of deviation (matrix) traces. Within the framework of classical error…

Instrumentation and Methods for Astrophysics · Physics 2011-03-08 R. Caimmi

We study least squares linear regression over $N$ uncorrelated Gaussian features that are selected in order of decreasing variance. When the number of selected features $p$ is at most the sample size $n$, the estimator under consideration…

Statistics Theory · Mathematics 2019-10-04 Ji Xu , Daniel Hsu

Importance weighting is a classic technique to handle distribution shifts. However, prior work has presented strong empirical and theoretical evidence demonstrating that importance weights can have little to no effect on overparameterized…

Machine Learning · Computer Science 2022-03-07 Ke Alexander Wang , Niladri S. Chatterji , Saminul Haque , Tatsunori Hashimoto

Since its early use in least squares regression problems, the l1-penalization framework for variable selection has been employed in conjunction with a wide range of loss functions encompassing regression, classification and survival…

Statistics Theory · Mathematics 2009-08-14 Guilherme V. Rocha , Xing Wang , Bin Yu

Overparametrization often helps improve the generalization performance. This paper presents a dual view of overparametrization suggesting that downsampling may also help generalize. Focusing on the proportional regime $m\asymp n \asymp p$,…

Statistics Theory · Mathematics 2023-10-17 Xin Chen , Yicheng Zeng , Siyue Yang , Qiang Sun

We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error. In these over-parameterized settings there are many global minima with zero training error, some of which generalize…

Machine Learning · Computer Science 2023-12-05 Julius Martinetz , Thomas Martinetz

Overparametrized interpolating models have drawn increasing attention from machine learning. Some recent studies suggest that regularized interpolating models can generalize well. This phenomenon seemingly contradicts the conventional…

Statistics Theory · Mathematics 2022-07-04 Bo Luan , Yoonkyung Lee , Yunzhang Zhu

We propose a new model for supervised learning to rank. In our model, the relevance labels are assumed to follow a categorical distribution whose probabilities are constructed based on a scoring function. We optimize the training objective…

Machine Learning · Computer Science 2020-02-19 Siamak Zamani Dadaneh , Shahin Boluki , Mingyuan Zhou , Xiaoning Qian