English
Related papers

Related papers: Extending the Use of MDL for High-Dimensional Prob…

200 papers

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

The minimum description length (MDL) principle in supervised learning is studied. One of the most important theories for the MDL principle is Barron and Cover's theory (BC theory), which gives a mathematical justification of the MDL…

Information Theory · Computer Science 2016-07-12 Masanori Kawakita , Jun'ichi Takeuchi

Minimum message length is a general Bayesian principle for model selection and parameter estimation that is based on information theory. This paper applies the minimum message length principle to a small-sample model selection problem…

Methodology · Statistics 2018-02-13 Chi Kuen Wong , Enes Makalic , Daniel F. Schmidt

Symbolic regression, a task discovering the formula best fitting the given data, is typically based on the heuristical search. These methods usually update candidate formulas to obtain new ones with lower prediction errors iteratively.…

Machine Learning · Computer Science 2025-09-11 Zihan Yu , Jingtao Ding , Yong Li , Depeng Jin

A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting, and produces an inferred network…

Machine Learning · Statistics 2025-03-24 Tiago P. Peixoto

We propose a deep neural network (DNN) based least distance (LD) estimator (DNN-LD) for a multivariate regression problem, addressing the limitations of the conventional methods. Due to the flexibility of a DNN structure, both linear and…

Methodology · Statistics 2024-01-09 Jungmin Shin , Seung Jun Shin , Sungwan Bang

Unsupervised discretization is a crucial step in many knowledge discovery tasks. The state-of-the-art method for one-dimensional data infers locally adaptive histograms using the minimum description length (MDL) principle, but the…

Machine Learning · Computer Science 2022-12-12 Lincen Yang , Mitra Baratchi , Matthijs van Leeuwen

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

This paper introduces a novel optimization framework that fundamentally integrates the Minimum Description Length (MDL) principle into the training dynamics of deep neural networks. Moving beyond its conventional role as a model selection…

Machine Learning · Computer Science 2026-03-16 Ming Lei , Shufan Wu , Christophe Baehr

Deep neural networks trained through end-to-end learning have achieved remarkable success across various domains in the past decade. However, the end-to-end learning strategy, originally designed to minimize predictive loss in a black-box…

Machine Learning · Computer Science 2025-06-11 Canlin Zhang , Xiuwen Liu

Most data sets comprise of measurements on continuous and categorical variables. In regression and classification Statistics literature, modeling high-dimensional mixed predictors has received limited attention. In this paper we study the…

Statistics Theory · Mathematics 2021-10-26 Efstathia Bura , Liliana Forzani , Rodrigo García Arancibia , Pamela Llop , Diego Tomassi

A major challenge in designing efficient statistical supervised learning algorithms is finding representations that perform well not only on available training samples but also on unseen data. While the study of representation learning has…

Machine Learning · Statistics 2024-02-06 Milad Sefidgaran , Abdellatif Zaidi , Piotr Krasnowski

Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and…

Image and Video Processing · Electrical Eng. & Systems 2025-04-04 Chicago Y. Park , Weijie Gan , Zihao Zou , Yuyang Hu , Zhixin Sun , Ulugbek S. Kamilov

To investigate the theoretical foundations of deep learning from the viewpoint of the minimum description length (MDL) principle, we analyse risk bounds of MDL estimators based on two-stage codes for simple two-layers neural networks (NNs)…

Information Theory · Computer Science 2024-11-19 Yoshinari Takeishi , Jun'ichi Takeuchi

Fast and effective unsupervised anomaly detection algorithms have been proposed for categorical data based on the minimum description length (MDL) principle. However, they can be ineffective when detecting anomalies in heterogeneous…

Databases · Computer Science 2020-06-16 James Cheney , Xavier Gombau , Ghita Berrada , Sidahmed Benabderrahmane

In this correspondence, we focus on the performance analysis of the widely-used minimum description length (MDL) source enumeration technique in array processing. Unfortunately, available theoretical analysis exhibit deviation from the…

Information Theory · Computer Science 2015-05-13 Farzan Haddadi , Mohammadreza Malekmohammadi , Mohammad Mahdi Nayebi , Mohammad Reza Aref

This paper aims to develop an optimality theory for linear discriminant analysis in the high-dimensional setting. A data-driven and tuning free classification rule, which is based on an adaptive constrained $\ell_1$ minimization approach,…

Methodology · Statistics 2018-04-10 T. Tony Cai , Linjun Zhang

The parametric complexity is the key quantity in the minimum description length (MDL) approach to statistical model selection. Rissanen and others have shown that the parametric complexity of a statistical model approaches a simple function…

Information Theory · Computer Science 2015-10-30 James G. Dowty

Most of the existing methods for estimating the local intrinsic dimension of a data distribution do not scale well to high-dimensional data. Many of them rely on a non-parametric nearest neighbors approach which suffers from the curse of…

A route recommendation system can provide better recommendation if it also takes collected user reviews into account, e.g. places that generally get positive reviews may be preferred. However, to classify sentiment, many classification…

Information Retrieval · Computer Science 2018-06-14 Diyah Puspitaningrum , I. S. W. B. Prasetya , P. A. Wicaksono