中文
相关论文

相关论文: Strong Asymptotic Assertions for Discrete MDL in R…

200 篇论文

Minimum Description Length (MDL) is an important principle for induction and prediction, with strong relations to optimal Bayesian learning. This paper deals with learning non-i.i.d. processes by means of two-part MDL, where the underlying…

信息论 · 计算机科学 2007-07-13 Jan Poland , Marcus Hutter

We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models. This applies in particular to the important case of…

机器学习 · 计算机科学 2011-11-09 Jan Poland , Marcus Hutter

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…

概率论 · 数学 2010-12-30 Marcus Hutter

The Minimum Description Length principle for online sequence estimation/prediction in a proper learning setup is studied. If the underlying model class is discrete, then the total expected square loss is a particularly interesting…

统计理论 · 数学 2007-07-16 Jan Poland , Marcus Hutter

We consider the Minimum Description Length principle for online sequence prediction. If the underlying model class is discrete, then the total expected square loss is a particularly interesting performance measure: (a) this quantity is…

机器学习 · 计算机科学 2007-07-16 Jan Poland , Marcus Hutter

The MDL two-part coding $ \textit{index of resolvability} $ provides a finite-sample upper bound on the statistical risk of penalized likelihood estimators over countable models. However, the bound does not apply to unpenalized maximum…

统计理论 · 数学 2018-01-01 W. D. Brinda , Jason M. Klusowski

This is an up-to-date introduction to and overview of the Minimum Description Length (MDL) Principle, a theory of inductive inference that can be applied to general problems in statistics, machine learning and pattern recognition. While MDL…

统计方法学 · 统计学 2019-12-19 Peter Grünwald , Teemu Roos

Consider the nonparametric logistic regression problem. In the logistic regression, we usually consider the maximum likelihood estimator, and the excess risk is the expectation of the Kullback-Leibler (KL) divergence between the true and…

统计理论 · 数学 2025-02-26 Atsutomo Yara , Yoshikazu Terada

The aim of this note is to state a couple of general results about the properties of the penalized maximum likelihood estimators (pMLE) and of the posterior distribution for parametric models in a non-asymptotic setup and for possibly large…

统计理论 · 数学 2022-12-13 Vladimir Spokoiny

We consider model selection in generalized linear models (GLM) for high-dimensional data and propose a wide class of model selection criteria based on penalized maximum likelihood with a complexity penalty on the model size. We derive a…

统计理论 · 数学 2016-03-31 Felix Abramovich , Vadim Grinshtein

In the signal processing and statistics literature, the minimum description length (MDL) principle is a popular tool for choosing model complexity. Successful examples include signal denoising and variable selection in linear regression,…

信号处理 · 电气工程与系统科学 2022-01-28 Zhenyu Wei , Raymond K. W. Wong , Thomas C. M. Lee

The asymptotic normality of the Maximum Likelihood Estimator (MLE) is a cornerstone of statistical theory. In the present paper, we provide sharp explicit upper bounds on Zolotarev-type distances between the exact, unknown distribution of…

统计理论 · 数学 2016-04-19 Andreas Anastasiou , Christophe Ley

We give an asymptotic development of the maximum likelihood estimator (MLE), or any other estimator defined implicitly, in a way which involves the limiting behavior of the score and its higher-order derivatives. This development, which is…

统计理论 · 数学 2024-04-10 Antoine Lejay , Sara Mazzonetto

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…

机器学习 · 统计学 2024-02-06 Milad Sefidgaran , Abdellatif Zaidi , Piotr Krasnowski

Maximum regularized likelihood estimators (MRLEs) are arguably the most established class of estimators in high-dimensional statistics. In this paper, we derive guarantees for MRLEs in Kullback-Leibler divergence, a general measure of…

机器学习 · 统计学 2018-10-18 Rui Zhuang , Johannes Lederer

Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), which predict that simpler models generalize better when data arises from low-complexity…

机器学习 · 计算机科学 2026-05-14 Lukas Silvester Barth , Paulo von Petersenn

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…

机器学习 · 计算机科学 2019-11-01 Hugo M. Proença , Matthijs van Leeuwen

Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions, has emerged as a unified framework in response to the evolving demand for robustness,…

机器学习 · 计算机科学 2025-08-12 Zihan Zhang , Wenhao Zhan , Yuxin Chen , Simon S. Du , Jason D. Lee

This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomonoff's universal prior M, the latter being an excellent…

信息论 · 计算机科学 2007-07-16 Marcus Hutter

We consider hidden Markov models indexed by a binary tree where the hidden state space is a general metric space. We study the maximum likelihood estimator (MLE) of the model parameters based only on the observed variables. In both…

概率论 · 数学 2025-08-20 Julien Weibel
‹ 上一页 1 2 3 10 下一页 ›