English
Related papers

Related papers: Estimation of the Learning Coefficient Using Empir…

200 papers

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

Watanabe's singular learning theory provides a framework for asymptotic analysis of Bayesian model selection for statistical models with singularities, where traditional statistical regularity assumptions fail. Learning coefficients, also…

Statistics Theory · Mathematics 2025-11-20 Mathias Drton , Elizabeth Gross , Dimitra Kosta , Anton Leykin , Seth Sullivant , Daniel Windisch

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

The widely applicable Bayesian information criterion (WBIC) is a simple and fast approximation to the model evidence that has received little practical consideration. WBIC uses the fact that the log evidence can be written as an…

Methodology · Statistics 2016-04-29 N. Friel , J. P. McKeone , C. J. Oates , A. N. Pettitt

Recent advances have clarified theoretical learning accuracy in Bayesian inference, revealing that the asymptotic behavior of metrics such as generalization loss and free energy, assessing predictive accuracy, is dictated by a rational…

Statistics Theory · Mathematics 2024-08-15 Yuki Kurumadani

The widely applicable information criterion (WAIC) has been used as a model selection criterion for Bayesian statistics in recent years. It is an asymptotically unbiased estimator of the Kullback-Leibler divergence between a Bayesian…

Methodology · Statistics 2022-08-09 Yoshiyuki Ninomiya

As an important branch of weakly supervised learning, partial label learning deals with data where each instance is assigned with a set of candidate labels, whereas only one of them is true. Despite many methodology studies on learning from…

Machine Learning · Computer Science 2021-06-11 Hongwei Wen , Jingyi Cui , Hanyuan Hang , Jiabin Liu , Yisen Wang , Zhouchen Lin

Watanabe-Akaike information criterion (WAIC; Watanabe, 2010) and leave-one-out cross validation (LOO) are two fully Bayesian model selection methods that have been shown to perform better than other traditional information-criterion based…

Applications · Statistics 2018-06-27 Luo Yong

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

Recent advances have clarified theoretical learning accuracy in Bayesian inference, revealing that the asymptotic behavior of metrics such as generalization loss and free energy, assessing predictive accuracy, is dictated by a rational…

Statistics Theory · Mathematics 2024-08-26 Yuki Kurumadani

A statistical model or a learning machine is called regular if the map taking a parameter to a probability distribution is one-to-one and if its Fisher information matrix is always positive definite. If otherwise, it is called singular. In…

Machine Learning · Computer Science 2012-09-03 Sumio Watanabe

In this article we propose a general class of risk measures which can be used for data based evaluation of parametric models. The loss function is defined as generalized quadratic distance between the true density and the proposed model.…

Statistics Theory · Mathematics 2007-10-02 Surajit Ray , Bruce G. Lindsay

The learning curve expresses the error rate of a predictive modeling procedure as a function of the sample size of the training dataset. It typically is a decreasing, convex function with a positive limiting value. An estimate of the…

Applications · Statistics 2012-03-14 Eric B. Laber , Kerby Shedden , Yang Yang

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Shichao Kan , Zhiquan He , Yigang Cen , Yang Li , Vladimir Mladenovic , Zhihai He

A central issue of many statistical learning problems is to select an appropriate model from a set of candidate models. Large models tend to inflate the variance (or overfitting), while small models tend to cause biases (or underfitting)…

Statistics Theory · Mathematics 2020-12-25 Jie Ding , Enmao Diao , Jiawei Zhou , Vahid Tarokh

The Information Bottleneck (IB) method (\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\beta I(Y;Z)$ employs a…

Machine Learning · Computer Science 2019-10-23 Tailin Wu , Ian Fischer , Isaac L. Chuang , Max Tegmark

We review the Akaike, deviance, and Watanabe-Akaike information criteria from a Bayesian perspective, where the goal is to estimate expected out-of-sample-prediction error using a biascorrected adjustment of within-sample error. We focus on…

Methodology · Statistics 2013-07-24 Andrew Gelman , Jessica Hwang , Aki Vehtari

A number of machine learning algorithms are using a metric, or a distance, in order to compare individuals. The Euclidean distance is usually employed, but it may be more efficient to learn a parametric distance such as Mahalanobis metric.…

Machine Learning · Computer Science 2016-12-16 Hoel Le Capitaine

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

This paper introduces an estimator of the relative directed distance between an estimated model and the true model, based on the Kulback-Leibler divergence and is motivated by the generalized information criterion proposed by Konishi and…

Methodology · Statistics 2014-03-06 Antonino Abbruzzo , Ivan Vujačić , Ernst Wit , Angelo M. Mineo
‹ Prev 1 2 3 10 Next ›