中文
相关论文

相关论文: On the power of random information

200 篇论文

In situations where it is difficult to enroll patients in randomized controlled trials, external data can improve efficiency and feasibility. In such cases, adaptive trial designs could be used to decrease enrollment in the control arm of…

统计方法学 · 统计学 2020-10-02 Brian D. Segal , W. Katherine Tan

We consider the problem of choosing the best of $n$ samples, out of a large random pool, when the sampling of each member is associated with a certain cost. The quality (worth) of the best sample clearly increases with $n$, but so do the…

统计理论 · 数学 2015-06-16 Joseph D. Skufca , Daniel ben-Avraham

Avoiding overfitting is a central challenge in machine learning, yet many large neural networks readily achieve zero training loss. This puzzling contradiction necessitates new approaches to the study of overfitting. Here we quantify…

信息论 · 计算机科学 2022-10-13 Vudtiwat Ngampruetikorn , David J. Schwab

Classical deterministic optimal control problems assume full information about the controlled process. The theory of control for general partially-observable processes is powerful, but the methods are computationally expensive and typically…

最优化与控制 · 数学 2024-08-02 Dongping Qi , Adam Dhillon , Alexander Vladimirsky

Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often sequentially aggregated reward, are often inherently…

机器学习 · 计算机科学 2019-09-06 Ameer Haj-Ali , Nesreen K. Ahmed , Ted Willke , Joseph Gonzalez , Krste Asanovic , Ion Stoica

This paper presents a new foundational approach to information theory based on the concept of the information efficiency of a recursive function, which is defined as the difference between the information in the input and the output. The…

信息论 · 计算机科学 2023-08-29 Pieter Adriaans

The evaluation of the probability of union of a large number of independent events requires several combinations involving the factorial and the use of high performance computers with several hours of processing. Bounds and simplifications…

数值分析 · 数学 2025-03-07 Edson Luiz Ursini , Paulo S. Martins

Current discrete randomness and information conservation inequalities are over total recursive functions, i.e. restricted to deterministic processing. This restriction implies that an algorithm can break algorithmic randomness conservation…

计算复杂性 · 计算机科学 2013-10-15 Samuel Epstein

We consider approximation problems for tensor product and additive random fields based on standard information in the average case setting. We also study the probabilistic setting of the mentioned problem for tensor products. The main…

概率论 · 数学 2019-07-04 Mikhail Lifshits , Marguerite Zani

Is our world just information? We argue that our current notion of information has one serious shortcoming: It is quite literally meaningless. We suggest a meaningful extension of the notion of information that is dynamic, internal,…

量子物理 · 物理学 2013-11-07 Olaf Dreyer

We consider the problem of robust polynomial regression, where one receives samples $(x_i, y_i)$ that are usually within $\sigma$ of a polynomial $y = p(x)$, but have a $\rho$ chance of being arbitrary adversarial outliers. Previously, it…

数据结构与算法 · 计算机科学 2017-08-11 Daniel Kane , Sushrut Karmalkar , Eric Price

We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on $n$ independent samples from them. Curiously, we show that estimating the IPM itself between…

统计理论 · 数学 2019-11-05 Tengyuan Liang

The purpose of writing this book is to suggest some improved estimators using auxiliary information in sampling schemes like simple random sampling and systematic sampling. This volume is a collection of five papers. The following problems…

统计理论 · 数学 2013-08-28 Rajesh Singh , Florentin Smarandache

Modern mainstream financial theory is underpinned by the efficient market hypothesis, which posits the rapid incorporation of relevant information into asset pricing. Limited prior studies in the operational research literature have…

应用统计 · 统计学 2023-09-07 Ben Moews

In this Chapter, we ask questions (1) What is the right way to measure the quality of information processing in a biological system? and (2) What can real-life organisms do in order to improve their performance in information-processing…

定量方法 · 定量生物学 2010-11-25 Ilya Nemenman

We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems,…

机器学习 · 计算机科学 2017-11-07 Aolin Xu , Maxim Raginsky

We introduce a relative variant of information loss to characterize the behavior of deterministic input-output systems. We show that the relative loss is closely related to Renyi's information dimension. We provide an upper bound for…

信息论 · 计算机科学 2012-04-02 Bernhard C. Geiger , Gernot Kubin

Recently, it has been claimed that a linear relationship between a measure of information content and word length is expected from word length optimization and it has been shown that this linearity is supported by a strong correlation…

数据分析、统计与概率 · 物理学 2019-12-11 Ramon Ferrer-i-Cancho , Fermín Moscoso del Prado Martín

Resource-constrained systems are prevalent in communications. Such a system is composed of many components but only some of them can be allocated with resources such as time slots. According to the amount of information about the system,…

信息论 · 计算机科学 2014-04-02 Albert Y. S. Lam , Yanhui Geng , Victor O. K. Li

Learning-to-rank techniques have proven to be extremely useful for prioritization problems, where we rank items in order of their estimated probabilities, and dedicate our limited resources to the top-ranked items. This work exposes a…

机器学习 · 统计学 2018-02-22 Cynthia Rudin , Yining Wang