English
Related papers

Related papers: General bound of overfitting for MLP regression mo…

200 papers

Linear Least Squares is a very well known technique for parameter estimation, which is used even when sub-optimal, because of its very low computational requirements and the fact that exact knowledge of the noise statistics is not required.…

Signal Processing · Electrical Eng. & Systems 2017-11-01 Michael Krikheli , Amir Leshem

We consider the problem of linear fitting of noisy data in the case of broad (say $\alpha$-stable) distributions of random impacts ("noise"), which can lack even the first moment. This situation, common in statistical physics of small…

Data Analysis, Statistics and Probability · Physics 2015-05-27 Eugene B. Postnikov , Igor M. Sokolov

We consider high-dimensional multiclass classification by sparse multinomial logistic regression. Unlike binary classification, in the multiclass setup one can think about an entire spectrum of possible notions of sparsity associated with…

Statistics Theory · Mathematics 2023-01-18 Tomer Levy , Felix Abramovich

Modern machine learning systems such as deep neural networks are often highly over-parameterized so that they can fit the noisy training data exactly, yet they can still achieve small test errors in practice. In this paper, we study this…

Machine Learning · Computer Science 2022-01-04 Yuan Cao , Quanquan Gu , Mikhail Belkin

Why heavily parameterized neural networks (NNs) do not overfit the data is an important long standing open question. We propose a phenomenological model of the NN training to explain this non-overfitting puzzle. Our linear frequency…

Machine Learning · Computer Science 2021-05-26 Yaoyu Zhang , Tao Luo , Zheng Ma , Zhi-Qin John Xu

Modern machine learning classifiers often exhibit vanishing classification error on the training set. They achieve this by learning nonlinear representations of the inputs that maps the data into linearly separable classes. Motivated by…

Statistics Theory · Mathematics 2023-03-23 Andrea Montanari , Feng Ruan , Youngtak Sohn , Jun Yan

Multi-layer perceptron (MLP) is a fundamental component of deep learning, and recent MLP-based architectures, especially the MLP-Mixer, have achieved significant empirical success. Nevertheless, our understanding of why and how the…

Machine Learning · Computer Science 2024-05-08 Tomohiro Hayase , Ryo Karakida

Mixed linear regression (MLR) model is among the most exemplary statistical tools for modeling non-linear distributions using a mixture of linear models. When the additive noise in MLR model is Gaussian, Expectation-Maximization (EM)…

Machine Learning · Statistics 2021-05-14 Babak Barazandeh , Ali Ghafelebashi , Meisam Razaviyayn , Ram Sriharsha

It is well-known that the distribution over functions induced through a zero-mean iid prior distribution over the parameters of a multi-layer perceptron (MLP) converges to a Gaussian process (GP), under mild conditions. We extend this…

Machine Learning · Computer Science 2019-12-02 Russell Tsuchida , Fred Roosta , Marcus Gallagher

In a regression context, when the relevant subset of explanatory variables is uncertain, it is common to use a data-driven model selection procedure. Classical linear model theory, applied naively to the selected sub-model, may not be valid…

Statistics Theory · Mathematics 2017-12-08 Liang Hong , Todd A. Kuffner , Ryan Martin

We present a fully constructive analysis of deep ReLU neural networks for classification and function approximation tasks. First, we prove that any dataset with $N$ distinct points in $\mathbb{R}^d$ and $M$ output classes can be exactly…

Machine Learning · Statistics 2025-06-25 Martín Hernández , Enrique Zuazua

A multilayer perceptron (MLP) is typically made of multiple fully connected layers with nonlinear activation functions. There have been several approaches to make them better (e.g. faster convergence, better convergence limit, etc.). But…

Machine Learning · Computer Science 2021-08-24 Taewoon Kim

Probabilistic models analyze data by relying on a set of assumptions. Data that exhibit deviations from these assumptions can undermine inference and prediction quality. Robust models offer protection against mismatch between a model's…

Machine Learning · Statistics 2018-06-20 Yixin Wang , Alp Kucukelbir , David M. Blei

In fitting a mixture of linear regression models, normal assumption is traditionally used to model the error and then regression parameters are estimated by the maximum likelihood estimators (MLE). This procedure is not valid if the normal…

Methodology · Statistics 2018-11-06 Yanyuan Ma , Shaoli Wang , Lin Xu , Weixin Yao

Linear Least Squares is a very well known technique for parameter estimation, which is used even when sub-optimal, because of its very low computational requirements and the fact that exact knowledge of the noise statistics is not required.…

Statistics Theory · Mathematics 2018-10-16 Michael Krikheli , Amir Leshem

We investigate the problem of machine learning with mislabeled training data. We try to make the effects of mislabeled training better understood through analysis of the basic model and equations that characterize the problem. This includes…

Machine Learning · Computer Science 2019-09-23 Herbert Gish , Jan Silovsky , Man-Ling Sung , Man-Hung Siu , William Hartmann , Zhuolin Jiang

We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspects: (i) MLPs formulate a family of Gibbs distributions, and…

Machine Learning · Computer Science 2020-06-18 Xinjie Lan , Xin Guo , Kenneth E. Barner

To estimate a sparse linear model from data with Gaussian noise, consilience from lasso and compressed sensing literatures is that thresholding estimators like lasso and the Dantzig selector have the ability in some situations to identify…

Machine Learning · Statistics 2017-08-14 Jairo Diaz-Rodriguez , Sylvain Sardy

Suppose data are fitted to some parametric model but that the true model happens to be one with an additional parameter. When a parameter is to be estimated one can use likelihood estimation in the wider model or in the narrow model.…

Methodology · Statistics 2026-03-27 Nils Lid Hjort

Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels. To address this issue, researchers have explored alternative loss functions that aim to be more robust. The…

Machine Learning · Computer Science 2024-08-23 William Toner , Amos Storkey