首页/论文/2012.08338

arXiv 2012.083382020-12-15math.STstat.TH

Asymptotic Behavior of Free Energy When Optimal Probability Distribution Is Not Unique

Shuya Nagayasu, Sumio Watanabe

备注：: 14 pages, 2 figures

英文摘要：

Bayesian inference is a widely used statistical method. The free energy and generalization loss, which are used to estimate the accuracy of Bayesian inference, are known to be small in singular models that do not have a unique optimal parameter. However, their characteristics are not yet known when there are multiple optimal probability distributions. In this paper, we theoretically derive the asymptotic behaviors of the generalization loss and free energy in the case that the optimal probability distributions are not unique and show that they contain asymptotically different terms from those of the conventional asymptotic analysis.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Lomax distribution and asymptotical ML estimations based on record values for probability density function and cumulative distribution function

Here in this paper, it is tried to obtain and compare the ML estimations based on upper record values and a random sample. In continue, some theorems have been proven about the behavior of these estimations asymptotically.

2021-05-17math.STstat.TH

Parallelism, Uniqueness, and Large-Sample Asymptotics for the Dantzig Selector

The Dantzig selector (Candes and Tao, 2007) is a popular l1-regularization method for variable selection and estimation in linear regression. We present a very weak geometric condition on the observed predictors which is related to parallelism and, when satisfied, ensures the uniqueness of Dantzig selector estimators. The condition holds with probability 1, if the predictors are drawn from a continuous distribution. We discuss the necessity of this condition for uniqueness and also provide a closely related condition which ensures uniqueness of lasso estimators (Tibshirani, 1996). Large sample…

2012-06-05math.STstat.TH

Asymptotically optimum estimation of a probability in inverse binomial sampling under general loss functions

The optimum quality that can be asymptotically achieved in the estimation of a probability p using inverse binomial sampling is addressed. A general definition of quality is used in terms of the risk associated with a loss function that satisfies certain assumptions. It is shown that the limit superior of the risk for p asymptotically small has a minimum over all (possibly randomized) estimators. This minimum is achieved by certain non-randomized estimators. The model includes commonly used quality criteria as particular cases. Applications to the non-asymptotic regime are discussed considerin…

2012-04-30math.STstat.TH

长期预测中的渐近唯一性

Asymptotic uniqueness in long-term prediction

针对无限期概率预测，本文证明两位预测者必有一人失信或预测在全变差距离下收敛，给出 Blackwell–Dubins 定理的博弈论推广并按激进概率主义加以强化。

2024-04-05math.STstat.TH

概率质量函数的归一化离散关联核估计量的渐近性质

Asymptotic properties of the normalized discrete associated-kernel estimator for probability mass function

本文研究概率质量函数归一化离散关联核估计量的渐近性质，证明归一化随机变量均方收敛到1，并推导估计量的一致性与渐近正态性，验证多种离散核满足条件且一阶二项核在模拟中表现良好。

2022-02-21math.STstat.TH

Asymptotic probability distribution of distances between local extrema of error terms of a moving average process

Consider error terms x(i) of a moving average process MA(q), where x(i)=e(i) + e(i-1)+...+e(i-q) and e(i) - independent identically distributed (i.i.d.) random variables. We recognize a term x(i) as a local maximum if the following condition holds true: x(i-1) < x(i) > x(i+1). If the local maximum x(i) is followed by the next local maxiumum x(k), then d=k-i is the distance between local maxima. The distances d(j) themselves are random vriables. In this paper we study the probability distribution of distances d(j). Particularly, we show that for any q>0 mean distance E[d(j)]=4 and asymptoticall…

2011-05-24math.STstat.TH

更多相关论文收起更多论文

Asymptotic Optimality in Bayesian Change-Point Detection Problems Under Global False Alarm Probability Constraint

In 1960s Shiryaev developed Bayesian theory of change detection in independent and identically distributed (i.i.d.) sequences. In Shiryaev's classical setting the goal is to minimize an average detection delay under the constraint imposed on the average probability of false alarm. Recently, Tartakovsky and Veeravalli (2005) developed a general Bayesian asymptotic change-point detection theory (in the classical setting) that is not limited to a restrictive i.i.d. assumption. It was proved that Shiryaev's detection procedure is asymptotically optimal under traditional average false alarm probabi…

2006-09-16math.PRmath.STstat.TH

Approximation of integrals over asymptotic sets with applications to probability and statistics

In this monograph, we prove an asymptotic approximation for integrals of probability densities over sets in finite dimensional euclidean space, which are far away from the origin (asymptotic sets). We use this approximation to investigate tails of quadratic forms of random vectors, supremum of random linear forms among others. Applications to the study of finite size random matrices, finite sample statistics of autoregressive processes, and supremum of some stochastic processes.

2003-12-05math.CAmath.PRmath.ST

Bootstrap prediction intervals with asymptotic conditional validity and unconditional guarantees

It can be argued that optimal prediction should take into account all available data. Therefore, to evaluate a prediction interval's performance one should employ conditional coverage probability, conditioning on all available observations. Focusing on a linear model, we derive the asymptotic distribution of the difference between the conditional coverage probability of a nominal prediction interval and the conditional coverage probability of a prediction interval obtained via a residual-based bootstrap. Applying this result, we show that a prediction interval generated by the residual-based b…

2021-02-27math.STstat.APstat.TH

M-方差的渐近性质与描述符的唯一性

M-Variance Asymptotics and Uniqueness of Descriptors

本文为M-估计中的样本损失最小值（M-方差）构建了渐近理论，利用其满足中心极限定理的特性提出假设检验，以判断总体损失函数是否存在多个全局最小值，并验证了其在非欧空间均值、非线性回归和高斯混合聚类中的应用。

2024-11-14math.STstat.MEstat.TH

Tail Asymptotics and Estimation for Elliptical Distributions

Let (X,Y) be a bivariate elliptical random vector with associated random radius in the Gumbel max-domain of attraction. In this paper we obtain a second order asymptotic expansion of the joint survival probability P(X > x, Y> y) for x,y large. Further, based on the asymptotic bounds we discuss some aspects of the statistical modelling of joint survival probabilities and the survival conditional excess probability.

2008-05-15math.PRmath.STstat.TH

增强随机过程网络：渐近极化概率及相关一般结果

Networks of reinforced stochastic processes: probability of asymptotic polarization and related general results

本文研究增强随机过程网络中智能体倾向的渐近极化问题，刻画极限取0或1的概率为零、严格正或一的条件，并给出基于[0,1]值鞅框架的概率估计技术。

2024-01-15math.PRmath.STstat.ME