English
Related papers

Related papers: Information Geometry and Asymptotic Theory for SMM…

200 papers

We introduce entropic strict minimum message length (SMML), a risk-sensitive generalization of strict minimum message length coding. The proposed criterion replaces expected two-part codelength under the prior predictive distribution with…

Statistics Theory · Mathematics 2026-05-20 Enes Makalic , Daniel F. Schmidt

The minimum message length principle is an information theoretic criterion that links data compression with statistical inference. This paper studies the strict minimum message length (SMML) estimator for $d$-dimensional exponential…

Information Theory · Computer Science 2014-03-24 James G. Dowty

The strict minimum message length (SMML) principle links data compression with inductive inference. The corresponding estimators have many useful properties but they can be hard to calculate. We investigate SMML estimators for linear…

Information Theory · Computer Science 2014-03-19 James G. Dowty

Strict Minimum Message Length (SMML) is an information-theoretic statistical inference method widely cited (but only with informal arguments) as providing estimations that are consistent for general estimation problems. It is, however,…

Machine Learning · Statistics 2020-01-07 Michael Brand

We analyze differences between two information-theoretically motivated approaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this…

Machine Learning · Computer Science 2013-02-01 Peter D Grunwald , Petri Kontkanen , Petri Myllymaki , Tomi Silander , Henry Tirri

A method is given for calculating the strict minimum message length (SMML) estimator for 1-dimensional exponential families with continuous sufficient statistics. A set of $n$ equations are found that the $n$ cut-points of the SMML…

Information Theory · Computer Science 2012-12-21 James G. Dowty

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

Distribution matching (DM) transforms independent and Bernoulli(1/2) distributed bits into a sequence of output symbols with a desired distribution. A fixed-to-fixed length, invertible DM architecture based on shell mapping is presented. It…

Information Theory · Computer Science 2018-12-14 Patrick Schulte , Fabian Steiner

We consider the lossless compression bound of any individual data sequence. If we fit the data by a parametric model, the entropy quantity $nH({\hat \theta}_n)$ obtained by plugging in the maximum likelihood estimate is an underestimate of…

Information Theory · Computer Science 2024-01-23 Lei M Li

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

Theory evaluation is a key problem in many areas: machine learning, scientific discovery, inverse engineering, decision making, software engineering, design, human sciences, etc. If we have a set of theories that are able to explain the…

Logic in Computer Science · Computer Science 2013-01-23 Héctor Castillo-Andreu

The Normalized Maximum Likelihood (NML) codelength, or stochastic complexity, represents a principled criterion for universal coding. While recent coarea-based formulations provided a calculation method for smooth models, this framework…

Machine Learning · Computer Science 2026-05-26 Trenton Lau , Gary P. T. Choi

In this work, we propose a novel information theoretic framework for dictionary learning (DL) and sparse coding (SC) on a statistical manifold (the manifold of probability distributions). Unlike the traditional DL and SC framework, our new…

Computer Vision and Pattern Recognition · Computer Science 2017-02-06 Rudrasis Chakraborty , Monami Banerjee , Victoria Crawford , Baba C. Vemuri

Mixture modelling involves explaining some observed evidence using a combination of probability distributions. The crux of the problem is the inference of an optimal number of mixture components and their corresponding parameters. This…

Machine Learning · Computer Science 2015-03-02 Parthan Kasarapu , Lloyd Allison

We present a novel algorithm for segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well…

Computer Vision and Pattern Recognition · Computer Science 2010-06-21 Hossein Mobahi , Shankar R. Rao , Allen Y. Yang , Shankar S. Sastry , Yi Ma

Shannon's information theory deliberately excludes message semantics. This paper develops a rigorous framework for semantic communication that integrates formal proof systems with Shannon-theoretic tools. We introduce an axiomatic…

Logic in Computer Science · Computer Science 2026-04-21 Jianfeng Xu

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

Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geometric consequences remain poorly understood. We develop a mathematical framework that…

Machine Learning · Computer Science 2026-03-25 Mohamed A. Mabrok

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

Cryptography and Security · Computer Science 2025-07-03 Haiyun He , Yepeng Liu , Ziqiao Wang , Yongyi Mao , Yuheng Bu

We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA), a novel approach to Large-Language Model (LLM) training that jointly improves reasoning, alignment and robustness by treating an organisation's…

Machine Learning · Computer Science 2025-10-17 Gareth Seneque , Lap-Hang Ho , Nafise Erfanian Saeedi , Jeffrey Molendijk , Ariel Kuperman , Tim Elson
‹ Prev 1 2 3 10 Next ›