English
Related papers

Related papers: Gibbs-Based Information Criteria and the Over-Para…

200 papers

In model selection literature, two classes of criteria perform well asymptotically in different situations: Bayesian information criterion (BIC) (as a representative) is consistent in selection when the true model is finite dimensional…

Statistics Theory · Mathematics 2012-02-03 Wei Liu , Yuhong Yang

We introduce a novel Information Criterion (IC), termed Learning under Singularity (LS), designed to enhance the functionality of the Widely Applicable Bayes Information Criterion (WBIC) and the Singular Bayesian Information Criterion…

Machine Learning · Statistics 2024-02-23 Lirui Liu , Joe Suzuki

Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estimates in the context of overparametrized neural networks.…

Machine Learning · Computer Science 2023-05-24 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

System identification aims to build models of dynamical systems from data. Traditionally, choosing the model requires the designer to balance between two goals of conflicting nature; the model must be rich enough to capture the system…

Machine Learning · Computer Science 2021-08-09 Antônio H. Ribeiro , Johannes N. Hendriks , Adrian G. Wills , Thomas B. Schön

Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…

Information Theory · Computer Science 2023-11-08 Yuyan Ni , Yanyan Lan , Ao Liu , Zhiming Ma

In Generalised Bayesian Inference (GBI), the learning rate and hyperparameters of the loss must be estimated. These inference-hyperparameters can't be estimated jointly with the other parameters, from the data, by giving them a prior.…

Methodology · Statistics 2026-05-18 Jeong Eun Lee , Sitong Liu , Geoff K. Nicholls

Popular statistical software provides Bayesian information criterion (BIC) for multilevel models or linear mixed models. However, it has been observed that the combination of statistical literature and software documentation has led to…

Methodology · Statistics 2022-06-24 Sun-Joo Cho , Hao Wu , Matthew Naveiras

Double descent is a phenomenon of over-parameterized statistical models such as deep neural networks which have a re-descending property in their risk function. As the complexity of the model increases, risk exhibits a U-shaped region due…

Machine Learning · Statistics 2025-10-16 Nick Polson , Vadim Sokolov

We emphasize that it is possible to improve the principle of unbiased risk estimation for model selection by addressing excess risk deviations in the design of penalization procedures. Indeed, we propose a modification of Akaike's…

Statistics Theory · Mathematics 2018-07-23 Adrien Saumard , Fabien Navarro

The Bayesian information criterion (BIC), defined as the observed data log likelihood minus a penalty term based on the sample size $N$, is a popular model selection criterion for factor analysis with complete data. This definition has also…

Machine Learning · Statistics 2022-04-21 Jianhua Zhao , Changchun Shang , Shulan Li , Ling Xin , Philip L. H. Yu

We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models. The recent empirical success of large-scale models has motivated several theoretical studies to investigate a scenario…

Machine Learning · Statistics 2021-03-16 Ryumei Nakada , Masaaki Imaizumi

Recent works demonstrated the existence of a double-descent phenomenon for the generalization error of neural networks, where highly overparameterized models escape overfitting and achieve good test performance, at odds with the standard…

Machine Learning · Computer Science 2024-04-02 Elizaveta Demyanenko , Christoph Feinauer , Enrico M. Malatesta , Luca Saglietti

Robust model-fitting to spectroscopic transitions is a requirement across many fields of science. The corrected Akaike and Bayesian information criteria (AICc and BIC) are most frequently used to select the optimal number of fitting…

Instrumentation and Methods for Astrophysics · Physics 2020-11-25 John K. Webb , Chung-Chi Lee , Robert F. Carswell , Dinko Milaković

Model selection in linear regression models is a major challenge when dealing with high-dimensional data where the number of available measurements (sample size) is much smaller than the dimension of the parameter space. Traditional methods…

Signal Processing · Electrical Eng. & Systems 2023-07-05 Prakash B. Gohain , Magnus Jansson

We consider a model for logistic regression where only a subset of features of size $p$ is used for training a linear classifier over $n$ training samples. The classifier is obtained by running gradient descent (GD) on logistic loss. For…

Machine Learning · Statistics 2020-05-12 Zeyu Deng , Abla Kammoun , Christos Thrampoulidis

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

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

In a Gaussian graphical model, the conditional independence between two variables are characterized by the corresponding zero entries in the inverse covariance matrix. Maximum likelihood method using the smoothly clipped absolute deviation…

Methodology · Statistics 2009-09-07 Xin Gao , Daniel Q. Pu , Yuehua Wu , Hong Xu

We consider approximate Bayesian model choice for model selection problems that involve models whose Fisher-information matrices may fail to be invertible along other competing submodels. Such singular models do not obey the regularity…

Methodology · Statistics 2016-03-24 Mathias Drton , Martyn Plummer

In statistical learning, models are classified as regular or singular depending on whether the mapping from parameters to probability distributions is injective. Most models with hierarchical structures or latent variables are singular, for…

Machine Learning · Statistics 2025-11-26 Naoki Hayashi , Takuro Kutsuna , Sawa Takamuku