English
Related papers

Related papers: The Interpolating Information Criterion for Overpa…

200 papers

Deep learning is renowned for its theory-practice gap, whereby principled theory typically fails to provide much beneficial guidance for implementation in practice. This has been highlighted recently by the benign overfitting phenomenon:…

Machine Learning · Statistics 2023-11-14 Liam Hodgkinson , Chris van der Heide , Robert Salomone , Fred Roosta , Michael W. Mahoney

Information criteria are an appropriate and widely used tool for solving model selection problems. However, different ways to use them exist, each leading to a more or less precise approximation of the sought model. In this paper, we mainly…

Statistics Theory · Mathematics 2007-06-13 Guilhem Coq , Olivier Alata , Marc Arnaudon , Christian Olivier

A regression model with more parameters than data points in the training data is overparametrized and has the capability to interpolate the training data. Based on the classical bias-variance tradeoff expressions, it is commonly assumed…

Machine Learning · Computer Science 2023-04-18 Tomas McKelvey

The use of Bayesian information criterion (BIC) in the model selection procedure is under the assumption that the observations are independent and identically distributed (i.i.d.). However, in practice, we do not always have i.i.d. samples.…

Applications · Statistics 2021-05-03 Nan Shen , Bárbara González

A widely applicable Bayesian information criterion (Watanabe, 2013) is applicable for both regular and singular models in the model selection problem. This criterion tends to overestimate the log marginal likelihood. We identify an…

Methodology · Statistics 2019-08-29 Toru Imai

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

For linear models with a diverging number of parameters, it has recently been shown that modified versions of Bayesian information criterion (BIC) can identify the true model consistently. However, in many cases there is little…

Methodology · Statistics 2011-07-26 Heng Lian

Model selection is the problem of distinguishing competing models, perhaps featuring different numbers of parameters. The statistics literature contains two distinct sets of tools, those based on information theory such as the Akaike…

Astrophysics · Physics 2014-10-13 Andrew R Liddle

We consider Bayesian model selection in generalized linear models that are high-dimensional, with the number of covariates p being large relative to the sample size n, but sparse in that the number of active covariates is small compared to…

Statistics Theory · Mathematics 2011-12-26 Rina Foygel , Mathias Drton

We present an information-theoretic framework for understanding overfitting and underfitting in machine learning and prove the formal undecidability of determining whether an arbitrary classification algorithm will overfit a dataset.…

Machine Learning · Computer Science 2020-11-10 Daniel Bashir , George D. Montanez , Sonia Sehra , Pedro Sandoval Segura , Julius Lauw

The bias-variance trade-off is a central concept in supervised learning. In classical statistics, increasing the complexity of a model (e.g., number of parameters) reduces bias but also increases variance. Until recently, it was commonly…

Machine Learning · Statistics 2022-03-25 Jason W. Rocks , Pankaj Mehta

We consider a generalization of an important class of high-dimensional inference problems, namely spiked symmetric matrix models, often used as probabilistic models for principal component analysis. Such paradigmatic models have recently…

Information Theory · Computer Science 2020-05-19 Jean Barbier , Galen Reeves

In the problem of selecting variables in a multivariate linear regression model, we derive new Bayesian information criteria based on a prior mixing a smooth distribution and a delta distribution. Each of them can be interpreted as a fusion…

Statistics Theory · Mathematics 2022-09-29 Haruki Kono , Tatsuya Kubokawa

This article revisits the fundamental problem of parameter selection for Gaussian process interpolation. By choosing the mean and the covariance functions of a Gaussian process within parametric families, the user obtains a family of…

Methodology · Statistics 2023-08-09 Sébastien Petit , Julien Bect , Paul Feliot , Emmanuel Vazquez

There is growing interest in Bayesian clinical trial designs with informative prior distributions, e.g. for extrapolation of adult data to pediatrics, or use of external controls. While the classical type I error is commonly used to…

Methodology · Statistics 2023-09-06 Nicky Best , Maxine Ajimi , Beat Neuenschwander , Gaelle Saint-Hilary , Simon Wandel

Recently, the benefit of heavily overparameterized models has been observed in machine learning tasks: models with enough capacity to easily cross the \emph{interpolation threshold} improve in generalization error compared to the classical…

High Energy Physics - Experiment · Physics 2025-09-03 Matthias Vigl , Lukas Heinrich

We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data. In particular, we consider simple…

Machine Learning · Statistics 2022-06-17 Chen Cheng , John Duchi , Rohith Kuditipudi

Model selection based on classical information criteria, such as BIC, is generally computationally demanding, but its properties are well studied. On the other hand, model selection based on parameter shrinkage by $\ell_1$-type penalties is…

Machine Learning · Statistics 2013-07-10 Kun Zhang , Heng Peng , Laiwan Chan , Aapo Hyvarinen

Double-descent refers to the unexpected drop in test loss of a learning algorithm beyond an interpolating threshold with over-parameterization, which is not predicted by information criteria in their classical forms due to the limitations…

Machine Learning · Computer Science 2023-11-15 Haobo Chen , Yuheng Bu , Gregory W. Wornell

Comparisons are made for the amount of agreement of the composite likelihood information criteria and their full likelihood counterparts when making decisions among the fits of different models, and some properties of penalty term for…

Statistics Theory · Mathematics 2014-10-17 Chi Tim Ng , Harry Joe
‹ Prev 1 2 3 10 Next ›