中文
相关论文

相关论文: Efficient Sample-optimal Learning of Gaussian Tree…

200 篇论文

We provide finite sample guarantees for the classical Chow-Liu algorithm (IEEE Trans.~Inform.~Theory, 1968) to learn a tree-structured graphical model of a distribution. For a distribution $P$ on $\Sigma^n$ and a tree $T$ on $n$ nodes, we…

数据结构与算法 · 计算机科学 2021-07-23 Arnab Bhattacharyya , Sutanu Gayen , Eric Price , N. V. Vinodchandran

In this paper, learning of tree-structured Gaussian graphical models from distributed data is addressed. In our model, samples are stored in a set of distributed machines where each machine has access to only a subset of features. A central…

机器学习 · 计算机科学 2018-12-05 Mostafa Tavassolipour , Seyed Abolfazl Motahari , Mohammad-Taghi Manzuri Shalmani

Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions such as the reliability of the empirical value, one must…

人工智能 · 计算机科学 2008-06-26 Marco Zaffalon , Marcus Hutter

Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions such as the reliability of the empirical value, one must…

人工智能 · 计算机科学 2014-08-08 Marco Zaffalon , Marcus Hutter

We develop optimal algorithms for learning undirected Gaussian trees and directed Gaussian polytrees from data. We consider both problems of distribution learning (i.e. in KL distance) and structure learning (i.e. exact recovery). The first…

机器学习 · 计算机科学 2024-02-12 Yuhao Wang , Ming Gao , Wai Ming Tai , Bryon Aragam , Arnab Bhattacharyya

The problem of learning tree-structured Gaussian graphical models from independent and identically distributed (i.i.d.) samples is considered. The influence of the tree structure and the parameters of the Gaussian distribution on the…

机器学习 · 统计学 2010-05-06 Vincent Y. F. Tan , Animashree Anandkumar , Alan S. Willsky

We investigate the sample complexity of mutual information and conditional mutual information testing. For conditional mutual information testing, given access to independent samples of a triple of random variables $(A, B, C)$ with unknown…

数据结构与算法 · 计算机科学 2025-06-05 Jan Seyfried , Sayantan Sen , Marco Tomamichel

We show that $n$-variable tree-structured Ising models can be learned computationally-efficiently to within total variation distance $\epsilon$ from an optimal $O(n \ln n/\epsilon^2)$ samples, where $O(\cdot)$ hides an absolute constant…

机器学习 · 计算机科学 2020-12-01 Constantinos Daskalakis , Qinxuan Pan

We revisit the problem of distribution learning within the framework of learning-augmented algorithms. In this setting, we explore the scenario where a probability distribution is provided as potentially inaccurate advice on the true,…

机器学习 · 计算机科学 2025-02-03 Arnab Bhattacharyya , Davin Choo , Philips George John , Themis Gouleakis

We present convincing empirical evidence for an effective and general strategy for building accurate small models. Such models are attractive for interpretability and also find use in resource-constrained environments. The strategy is to…

机器学习 · 计算机科学 2024-04-30 Abhishek Ghose

We provide time- and sample-efficient algorithms for learning and testing latent-tree Ising models, i.e. Ising models that may only be observed at their leaf nodes. On the learning side, we obtain efficient algorithms for learning a…

机器学习 · 计算机科学 2023-07-11 Davin Choo , Yuval Dagan , Constantinos Daskalakis , Anthimos Vardis Kandiros

In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…

数据结构与算法 · 计算机科学 2023-06-02 Daniel Alabi , Pravesh K. Kothari , Pranay Tankala , Prayaag Venkat , Fred Zhang

Estimating mutual information (MI) from samples is a fundamental problem in statistics, machine learning, and data analysis. Recently it was shown that a popular class of non-parametric MI estimators perform very poorly for strongly…

信息论 · 计算机科学 2016-02-18 Shuyang Gao , Greg Ver Steeg , Aram Galstyan

This paper studies the decentralized learning of tree-structured Gaussian graphical models (GGMs) from noisy data. In decentralized learning, data set is distributed across different machines (sensors), and GGMs are widely used to model…

机器学习 · 计算机科学 2021-09-23 Akram Hussain

Joint distributions over many variables are frequently modeled by decomposing them into products of simpler, lower-dimensional conditional distributions, such as in sparsely connected Bayesian networks. However, automatically learning such…

机器学习 · 计算机科学 2013-01-07 Scott Davies , Andrew Moore

The accuracy of probability distributions inferred using machine-learning algorithms heavily depends on data availability and quality. In practical applications it is therefore fundamental to investigate the robustness of a statistical…

机器学习 · 统计学 2018-10-01 Christiane Goergen , Manuele Leonelli

This paper is concerned with the reliable inference of optimal tree-approximations to the dependency structure of an unknown distribution generating data. The traditional approach to the problem measures the dependency strength between…

机器学习 · 计算机科学 2007-07-16 Marco Zaffalon , Marcus Hutter

We describe a general technique that yields the first {\em Statistical Query lower bounds} for a range of fundamental high-dimensional learning problems involving Gaussian distributions. Our main results are for the problems of (1) learning…

机器学习 · 计算机科学 2017-05-18 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

Feature selection is one of the most fundamental problems in machine learning. An extensive body of work on information-theoretic feature selection exists which is based on maximizing mutual information between subsets of features and class…

机器学习 · 统计学 2016-06-10 Shuyang Gao , Greg Ver Steeg , Aram Galstyan

The perspective of developing trustworthy AI for critical applications in science and engineering requires machine learning techniques that are capable of estimating their own uncertainty. In the context of regression, instead of estimating…

机器学习 · 计算机科学 2026-05-14 Quentin Duchemin , Guillaume Obozinski
‹ 上一页 1 2 3 10 下一页 ›