English
Related papers

Related papers: A Short Introduction to Model Selection, Kolmogoro…

200 papers

The effort to understand network systems in increasing detail has resulted in a diversity of methods designed to extract their large-scale structure from data. Unfortunately, many of these methods yield diverging descriptions of the same…

Data Analysis, Statistics and Probability · Physics 2015-03-27 Tiago P. Peixoto

Machine learning (ML) models are typically optimized for their accuracy on a given dataset. However, this predictive criterion rarely captures all desirable properties of a model, in particular how well it matches a domain expert's…

Machine Learning · Computer Science 2022-07-07 Damien Teney , Maxime Peyrard , Ehsan Abbasnejad

In the Minimum Description Length (MDL) principle, learning from the data is equivalent to an optimal coding problem. We show that the codes that achieve optimal compression in MDL are critical in a very precise sense. First, when they are…

Methodology · Statistics 2018-10-03 Ryan John Cubero , Matteo Marsili , Yasser Roudi

In 1974 Kolmogorov proposed a non-probabilistic approach to statistics and model selection. Let data be finite binary strings and models be finite sets of binary strings. Consider model classes consisting of models of given maximal…

Computational Complexity · Computer Science 2007-05-23 Nikolai Vereshchagin , Paul Vitanyi

The Minimum Description Length (MDL) principle selects the model that has the shortest code for data plus model. We show that for a countable class of models, MDL predictions are close to the true distribution in a strong sense. The result…

Probability · Mathematics 2010-12-30 Marcus Hutter

We present an information-theoretic framework for understanding overfitting and underfitting in machine learning and prove the formal undecidability of determining whether an arbitrary classification algorithm will overfit a dataset.…

Machine Learning · Computer Science 2020-11-10 Daniel Bashir , George D. Montanez , Sonia Sehra , Pedro Sandoval Segura , Julius Lauw

We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representation that achieves…

Machine Learning · Computer Science 2021-02-08 William F. Whitney , Min Jae Song , David Brandfonbrener , Jaan Altosaar , Kyunghyun Cho

The amount of information in the form of features and variables avail- able to machine learning algorithms is ever increasing. This can lead to classifiers that are prone to overfitting in high dimensions, high di- mensional models do not…

Machine Learning · Computer Science 2014-02-12 Aaron Karper

Time-invariant linear dynamical system arises in many real-world applications,and its usefulness is widely acknowledged. A practical limitation with this model is that its latent dimension that has a large impact on the model capability…

Machine Learning · Computer Science 2019-06-25 Yang Li

We use decision theory to confront uncertainty that is sufficiently broad to incorporate "models as approximations." We presume the existence of a featured collection of what we call "structured models" that have explicit substantive…

Theoretical Economics · Economics 2022-08-22 Simone Cerreia-Vioglio , Lars Peter Hansen , Fabio Maccheroni , Massimo Marinacci

This is a short introduction to Kolmogorov Complexity. The interested reader is referred to the text books by Cover & Thomas as well as Li & V\'itanyi, which cover the fields of information theory and Kolmogorov complexity in depth and with…

Computational Complexity · Computer Science 2010-05-17 Volker Nannen

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

The (non-)equivalence of canonical and microcanonical ensembles is a fundamental question in statistical physics, concerning whether the use of soft and hard constraints in the maximum-entropy construction leads to the same description of a…

Statistical Mechanics · Physics 2025-11-25 Francesca Giuffrida , Tiziano Squartini , Peter Grünwald , Diego Garlaschelli

Overfitting describes a machine learning phenomenon where the model fits too closely to the training data, resulting in poor generalization. While this occurrence is thoroughly documented for many forms of supervised learning, it is not…

Machine Learning · Computer Science 2024-08-23 Zachary Rabin , Jim Davis , Benjamin Lewis , Matthew Scherreik

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

Random network models, constrained to reproduce specific statistical features, are often used to represent and analyze network data and their mathematical descriptions. Chief among them, the configuration model constrains random networks by…

Social and Information Networks · Computer Science 2025-01-28 Laurent Hébert-Dufresne , Jean-Gabriel Young , Alexander Daniels , Alec Kirkley , Antoine Allard

Recommender systems support decisions in various domains ranging from simple items such as books and movies to more complex items such as financial services, telecommunication equipment, and software systems. In this context,…

Information Retrieval · Computer Science 2021-02-15 Alexander Felfernig , Viet-Man Le , Andrei Popescu , Mathias Uta , Thi Ngoc Trang Tran , Müslüum Atas

Although much of the success of Deep Learning builds on learning good representations, a rigorous method to evaluate their quality is lacking. In this paper, we treat the evaluation of representations as a model selection problem and…

Machine Learning · Computer Science 2024-11-19 Yazhe Li , Jorg Bornschein , Marcus Hutter

Information distance is a parameter-free similarity measure based on compression, used in pattern recognition, data mining, phylogeny, clustering, and classification. The notion of information distance is extended from pairs to multiples…

Computer Vision and Pattern Recognition · Computer Science 2009-05-21 Paul M. B. Vitanyi

We demonstrate some novel links between entropy and description complexity, a notion referring to the minimal formula length for specifying given properties. Let MLU be the logic obtained by extending propositional logic with the universal…

Logic · Mathematics 2022-09-27 Reijo Jaakkola , Antti Kuusisto , Miikka Vilander