中文
相关论文

相关论文: On the Practical Estimation and Interpretation of …

200 篇论文

We investigate the effectiveness of the stabilizer R\'enyi entropy (SRE), a quantifier associated with non-stabilizer resources (quantum magic), as an indicator of quantum phase transitions. Specifically, we analyze the behavior of the…

量子物理 · 物理学 2026-05-19 Santanu Sarkar , George Biswas , Jun-Yi Wu , Anindya Biswas

Shannon and Renyi entropies are quantitative measures of uncertainty in a data set. They are developed by Renyi in the context of entropy theory. These measures have been studied in the case of the multivariate t-distributions. We extend…

统计理论 · 数学 2019-01-31 Salah H. Abid , Uday J. Quaez

It was recently shown that estimating the Shannon entropy $H({\rm p})$ of a discrete $k$-symbol distribution ${\rm p}$ requires $\Theta(k/\log k)$ samples, a number that grows near-linearly in the support size. In many applications $H({\rm…

信息论 · 计算机科学 2016-03-11 Jayadev Acharya , Alon Orlitsky , Ananda Theertha Suresh , Himanshu Tyagi

The Renyi entropies constitute a family of information measures that generalizes the well-known Shannon entropy, inheriting many of its properties. They appear in the form of unconditional and conditional entropies, relative entropies or…

量子物理 · 物理学 2014-01-28 Martin Müller-Lennert , Frédéric Dupuis , Oleg Szehr , Serge Fehr , Marco Tomamichel

Numerous entropy-type characteristics (functionals) generalizing R\'enyi entropy are widely used in mathematical statistics, physics, information theory, and signal processing for characterizing uncertainty in probability distributions and…

统计理论 · 数学 2011-03-28 David Källberg , Nikolaj Leonenko , Oleg Seleznjev

Current neural networks architectures are many times harder to train because of the increasing size and complexity of the used datasets. Our objective is to design more efficient training algorithms utilizing causal relationships inferred…

机器学习 · 计算机科学 2021-05-03 Adrian Moldovan , Angel Caţaron , Răzvan Andonie

The Matrix-based Renyi's entropy enables us to directly measure information quantities from given data without the costly probability density estimation of underlying distributions, thus has been widely adopted in numerous statistical…

机器学习 · 统计学 2022-05-17 Yuxin Dong , Tieliang Gong , Shujian Yu , Chen Li

We study the relative R\'enyi entropy (RRE) under local quenches in two-dimensional conformal field theories (CFTs), focusing on rational CFTs (RCFTs) and holographic CFTs. In RCFTs, the RRE evolves as a monotonic function over time,…

高能物理 - 理论 · 物理学 2025-12-22 Zi-Xuan Zhao , Song He , Hao Ouyang , Hong-an Zeng , Yu-Xuan Zhang

Information theoretic quantities play a central role in machine learning. The recent surge in the complexity of data and models has increased the demand for accurate estimation of these quantities. However, as the dimension grows the…

机器学习 · 统计学 2024-05-21 Viktor Nilsson , Anirban Samaddar , Sandeep Madireddy , Pierre Nyquist

Transfer entropy (TE) is a powerful tool for measuring causal relationships within interaction networks. Traditionally, TE and its conditional variants are applied pairwise between dynamic variables to infer these causal relationships.…

统计力学 · 物理学 2024-10-02 Julian Lee

R\'enyi entropy is an important measure in the context of information theory as a generalization of Shannon entropy. This information measure was often used for uncertainty quantification of dynamical behaviour of stochastic processes. In…

统计理论 · 数学 2025-10-28 Salah H. Abid , Uday J. Quaez , Javier E. Contreras-Reyescor

Data partitioning that maximizes/minimizes the Shannon entropy, or more generally the R\'enyi entropy is a crucial subroutine in data compression, columnar storage, and cardinality estimation algorithms. These partition algorithms can be…

数据结构与算法 · 计算机科学 2025-11-05 Aryan Esmailpour , Sanjay Krishnan , Stavros Sintos

The matrix-based R\'enyi's entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it widely applied in statistical…

机器学习 · 计算机科学 2022-12-01 Yuxin Dong , Tieliang Gong , Shujian Yu , Hong Chen , Chen Li

Modern learning systems excel at interpolation but struggle to generalize to unseen tasks outside the training distribution's support. This failure occurs even in simple settings, such as handling task parameters beyond the training range,…

机器学习 · 计算机科学 2026-05-29 Adam Ousherovitch , Yixin Wang

Distance measures between quantum states like the trace distance and the fidelity can naturally be defined by optimizing a classical distance measure over all measurement statistics that can be obtained from the respective quantum states.…

量子物理 · 物理学 2017-11-09 Mario Berta , Omar Fawzi , Marco Tomamichel

Following a recent proof of Shannon's entropy power inequality (EPI), a comprehensive framework for deriving various EPIs for the R\'enyi entropy is presented that uses transport arguments from normal densities and a change of variable by…

信息论 · 计算机科学 2018-10-17 Olivier Rioul

Configurational entropy, or complexity, plays a critical role in characterizing disordered systems such as glasses, yet its measurement often requires significant computational resources. Recently, R\'enyi entropy, a one-parameter…

无序系统与神经网络 · 物理学 2025-08-27 Nina Javerzat , Eric Bertin , Misaki Ozawa

Shannon entropy is not the only entropy that is relevant to machine-learning datasets, nor possibly even the most important one. Traditional entropies such as Shannon entropy capture information represented by elements' frequencies but not…

信息论 · 计算机科学 2026-04-01 Phuc Nguyen , Josiah Couch , Rahul Bansal , Alexandra Morgan , Chris Tam , Miao Li , Rima Arnaout , Ramy Arnaout

This paper provides tight bounds on the R\'enyi entropy of a function of a discrete random variable with a finite number of possible values, where the considered function is not one-to-one. To that end, a tight lower bound on the R\'enyi…

信息论 · 计算机科学 2018-12-11 Igal Sason

An uncertainty relation for the R\'enyi entropies of conjugate quantum observables is used to obtain a strong Heisenberg limit of the form ${\rm RMSE} \geq f(\alpha)/(\langle N\rangle+\frac12)$, bounding the root mean square error of any…

量子物理 · 物理学 2022-11-21 Michael J. W. Hall