English
Related papers

Related papers: An Empirical Study of MDL Model Selection with Inf…

200 papers

A salient approach to interpretable machine learning is to restrict modeling to simple models. In the Bayesian framework, this can be pursued by restricting the model structure and prior to favor interpretable models. Fundamentally,…

Machine Learning · Computer Science 2020-09-08 Homayun Afrabandpey , Tomi Peltola , Juho Piironen , Aki Vehtari , Samuel Kaski

Learning the structure of Bayesian networks and causal relationships from observations is a common goal in several areas of science and technology. We show that the prequential minimum description length principle (MDL) can be used to…

Machine Learning · Computer Science 2021-07-13 Jorg Bornschein , Silvia Chiappa , Alan Malek , Rosemary Nan Ke

Bayesian inference in deep neural networks is challenging due to the high-dimensional, strongly multi-modal parameter posterior density landscape. Markov chain Monte Carlo approaches asymptotically recover the true posterior but are…

Bayesian methods are appealing in their flexibility in modeling complex data and ability in capturing uncertainty in parameters. However, when Bayes' rule does not result in tractable closed-form, most approximate inference algorithms lack…

Machine Learning · Computer Science 2016-05-09 Bo Dai , Niao He , Hanjun Dai , Le Song

This paper deals with Bayesian inference of a mixture of Gaussian distributions. A novel formulation of the mixture model is introduced, which includes the prior constraint that each Gaussian component is always assigned a minimal number of…

Methodology · Statistics 2014-05-21 Colin J. Stoneking

Choosing the number of mixture components remains an elusive challenge. Model selection criteria can be either overly liberal or conservative and return poorly-separated components of limited practical use. We formalize non-local priors…

Methodology · Statistics 2019-06-12 Jairo Fúquene , Mark Steel , David Rossell

Despite exceptional predictive performance of Deep sequence models (DSMs), the main concern of their deployment centers around the lack of uncertainty awareness. In contrast, probabilistic models quantify the uncertainty associated with…

Machine Learning · Computer Science 2026-03-03 Wenlong Chen

In this paper we introduce objective proper prior distributions for hypothesis testing and model selection based on measures of divergence between the competing models; we call them divergence based (DB) priors. DB priors have simple forms…

Methodology · Statistics 2009-02-27 M. J. Bayarri , G. García-Donato

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

Interpretable classifiers have recently witnessed an increase in attention from the data mining community because they are inherently easier to understand and explain than their more complex counterparts. Examples of interpretable…

Machine Learning · Computer Science 2019-11-01 Hugo M. Proença , Matthijs van Leeuwen

Variable selection and classification are common objectives in the analysis of high-dimensional data. Most such methods make distributional assumptions that may not be compatible with the diverse families of distributions data can take. A…

Methodology · Statistics 2019-08-28 Weichang Yu , Lamiae Azizi , John T. Ormerod

Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification…

Machine Learning · Computer Science 2026-05-19 Boning Zhang , Matteo Zecchin , Mingzhao Guo , Dongzhu Liu , Osvaldo Simeone

A general Bayesian framework for model selection on random network models regarding their features is considered. The goal is to develop a principle Bayesian model selection approach to compare different fittable, not necessarily nested,…

Methodology · Statistics 2020-04-30 Papamichalis Marios

Mathematical models are invaluable for understanding and predicting how biological systems behave, although their construction requires specifying mechanisms and relationships that are often not perfectly known. In the presence of multiple…

Reasoning with minimal models has always been at the core of many knowledge representation techniques, but we still have only a limited understanding of this problem in Description Logics (DLs). Minimization of some selected predicates,…

Artificial Intelligence · Computer Science 2025-08-08 Federica Di Stefano , Quentin Manière , Magdalena Ortiz , Mantas Šimkus

Bayesian model selection poses two main challenges: the specification of parameter priors for all models, and the computation of the resulting Bayes factors between models. There is now a large literature on automatic and objective…

Methodology · Statistics 2016-08-11 Leonhard Held , Daniel Sabanés Bové , Isaac Gravestock

We demonstrate that the principle of maximum relative entropy (ME), used judiciously, can ease the specification of priors in model selection problems. The resulting effect is that models that make sharp predictions are disfavoured,…

Data Analysis, Statistics and Probability · Physics 2009-12-07 Brendon J. Brewer , Matthew J. Francis

This research develops a Bayesian framework for analyzing failure times using the Weibull distribution, addressing challenges in prior selection due to the lack of conjugate priors and multi-dimensional sufficient statistics. We propose an…

Methodology · Statistics 2025-06-16 Tobias Oketch , Mohammad Sepehrifar

Networks are fundamental models for data used in practically every application domain. In most instances, several implicit or explicit choices about the network definition impact the translation of underlying data to a network…

Artificial Intelligence · Computer Science 2018-01-12 Ivan Brugere , Tanya Y. Berger-Wolf

We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization,…

Machine Learning · Statistics 2025-10-15 Einar Urdshals , Edmund Lau , Jesse Hoogland , Stan van Wingerden , Daniel Murfet