English
Related papers

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

200 papers

We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ''posterior'' predictor with its KL divergence to a pre-specified ''prior''. This can be seen as an extension of a modified…

Machine Learning · Statistics 2026-03-25 Xiaohan Zhu , Mesrob I. Ohannessian , Nathan Srebro

In this work, we propose a modified Bayesian Information Criterion (BIC) specifically designed for mixture models and hierarchical structures. This criterion incorporates the determinant of the Hessian matrix of the log-likelihood function,…

In recent several years, the information bottleneck (IB) principle provides an information-theoretic framework for deep multi-view clustering (MVC) by compressing multi-view observations while preserving the relevant information of multiple…

Information Theory · Computer Science 2024-03-26 Xiaoqiang Yan , Zhixiang Jin , Fengshou Han , Yangdong Ye

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

In this paper, we studied two identically-trained neural networks (i.e. networks with the same architecture, trained on the same dataset using the same algorithm, but with different initialization) and found that their outputs discrepancy…

Machine Learning · Computer Science 2023-05-26 Yifan Luo , Bin Dong

Classical statistical learning theory predicts a U-shaped relationship between test loss and model capacity, driven by the bias-variance trade-off. Recent advances in modern machine learning have revealed a more complex pattern,…

Machine Learning · Statistics 2026-04-23 Yin Liu , Jianwen Cai , Didong Li

Recent progress has shown that the generalization error of the Gibbs algorithm can be exactly characterized using the symmetrized KL information between the learned hypothesis and the entire training dataset. However, evaluating such a…

Information Theory · Computer Science 2024-10-17 Youheng Zhu , Yuheng Bu

The standard Bayesian Information Criterion (BIC) is derived under regularity conditions which are not always satisfied by the graphical models with hidden variables. In this paper we derive the BIC score for Bayesian networks in the case…

Statistics Theory · Mathematics 2015-03-17 Piotr Zwiernik

Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon…

Machine Learning · Computer Science 2024-04-26 Yufei Gu , Xiaoqing Zheng , Tomaso Aste

Deep neural networks suffer from poor generalization to unseen environments when the underlying data distribution is different from that in the training set. By learning minimum sufficient representations from training data, the information…

Machine Learning · Computer Science 2021-10-13 Francesco Alesiani , Shujian Yu , Xi Yu

The Information Bottleneck (IB) framework is a general characterization of optimal representations obtained using a principled approach for balancing accuracy and complexity. Here we present a new framework, the Dual Information Bottleneck…

Information Theory · Computer Science 2020-06-09 Zoe Piran , Ravid Shwartz-Ziv , Naftali Tishby

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

Machine Learning · Computer Science 2024-05-24 Ling Han , Hao Huang , Dustin Scheinost , Mary-Anne Hartley , María Rodríguez Martínez

The relationship between the number of training data points, the number of parameters, and the generalization capabilities of models has been widely studied. Previous work has shown that double descent can occur in the over-parameterized…

Machine Learning · Statistics 2024-10-28 Xinyue Li , Rishi Sonthalia

The Akaike information criterion (AIC) is a model selection criterion widely used in practical applications. The AIC is an estimator of the log-likelihood expected value, and measures the discrepancy between the true model and the estimated…

Computation · Statistics 2017-02-03 Fábio M. Bayer , Francisco Cribari-Neto

`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized. The current theoretical understanding behind the occurrence of this phenomenon is primarily based on…

Machine Learning · Statistics 2022-03-15 Sidak Pal Singh , Aurelien Lucchi , Thomas Hofmann , Bernhard Schölkopf

We develop a closed form asymptotic formula to compute the marginal likelihood of data given a naive Bayesian network model with two hidden states and binary features. This formula deviates from the standard BIC score. Our work provides a…

Artificial Intelligence · Computer Science 2013-01-07 Dmitry Rusakov , Dan Geiger

In this paper a novel biclustering algorithm based on artificial intelligence (AI) is introduced. The method called EBIC aims to detect biologically meaningful, order-preserving patterns in complex data. The proposed algorithm is probably…

Machine Learning · Computer Science 2018-07-27 Patryk Orzechowski , Moshe Sipper , Xiuzhen Huang , Jason H. Moore

In statistical modeling area, the Akaike information criterion AIC, is a widely known and extensively used tool for model choice. The {\phi}-divergence test statistic is a recently developed tool for statistical model selection. The…

Methodology · Statistics 2011-10-28 Papa Ngom , Bertrand Ntep

We study a distributed learning problem in which Alice sends a compressed distillation of a set of training data to Bob, who uses the distilled version to best solve an associated learning problem. We formalize this as a rate-distortion…

Information Theory · Computer Science 2018-10-30 Parinaz Farajiparvar , Ahmad Beirami , Matthew Nokleby

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Machine Learning · Statistics 2020-11-09 Ben Adlam , Jeffrey Pennington