首页 > 最新文献

arXiv - STAT - Statistics Theory最新文献

英文 中文
Asymptotics for conformal inference 保角推理的渐近论
Pub Date : 2024-09-18 DOI: arxiv-2409.12019
Ulysse Gazin
Conformal inference is a versatile tool for building prediction sets inregression or classification. In this paper, we consider the false coverageproportion (FCP) in a transductive setting with a calibration sample of npoints and a test sample of m points. We identify the exact, distribution-free,asymptotic distribution of the FCP when both n and m tend to infinity. Thisshows in particular that FCP control can be achieved by using the well-knownKolmogorov distribution, and puts forward that the asymptotic variance isdecreasing in the ratio n/m. We then provide a number of extensions byconsidering the novelty detection problem, weighted conformal inference anddistribution shift between the calibration sample and the test sample. Inparticular, our asymptotical results allow to accurately quantify theasymptotical behavior of the errors when weighted conformal inference is used.
共形推理是建立回归或分类预测集的通用工具。在本文中,我们考虑了在具有 n 个点的校准样本和 m 个点的测试样本的反演环境中的虚假覆盖率(FCP)。我们确定了当 n 和 m 都趋于无穷大时,FCP 的精确、无分布、渐近分布。这特别表明,使用著名的科尔莫戈罗夫分布可以实现 FCP 控制,并提出渐近方差随 n/m 之比递减。然后,我们通过考虑新颖性检测问题、加权保形推理以及校准样本和测试样本之间的分布偏移,提出了一些扩展方法。特别是,当使用加权保形推理时,我们的渐近结果可以准确量化误差的渐近行为。
{"title":"Asymptotics for conformal inference","authors":"Ulysse Gazin","doi":"arxiv-2409.12019","DOIUrl":"https://doi.org/arxiv-2409.12019","url":null,"abstract":"Conformal inference is a versatile tool for building prediction sets in\u0000regression or classification. In this paper, we consider the false coverage\u0000proportion (FCP) in a transductive setting with a calibration sample of n\u0000points and a test sample of m points. We identify the exact, distribution-free,\u0000asymptotic distribution of the FCP when both n and m tend to infinity. This\u0000shows in particular that FCP control can be achieved by using the well-known\u0000Kolmogorov distribution, and puts forward that the asymptotic variance is\u0000decreasing in the ratio n/m. We then provide a number of extensions by\u0000considering the novelty detection problem, weighted conformal inference and\u0000distribution shift between the calibration sample and the test sample. In\u0000particular, our asymptotical results allow to accurately quantify the\u0000asymptotical behavior of the errors when weighted conformal inference is used.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An exponential inequality for Hilbert-valued U-statistics of i.i.d. data i.i.d. 数据的希尔伯特值 U 统计指数不等式
Pub Date : 2024-09-18 DOI: arxiv-2409.11737
Davide GiraudoIRMA
In this paper, we establish an exponential inequality for U-statistics ofi.i.d. data, varying kernel and taking values in a separable Hilbert space. Thebound are expressed as a sum of an exponential term plus an other one involvingthe tail of a sum of squared norms. We start by the degenerate case. Then weprovide applications to U-statistics of not necessarily degenerate fixedkernel, weighted U-statistics and incomplete U-statistics.
在本文中,我们建立了一个指数不等式,用于 i.i.d. 数据、变化内核和在可分离的希尔伯特空间中取值的 U 统计量。边界表示为一个指数项加上另一个涉及平方准则之和尾部的总和。我们首先讨论退化情况。然后,我们将其应用于不一定是退化定核的 U 统计、加权 U 统计和不完全 U 统计。
{"title":"An exponential inequality for Hilbert-valued U-statistics of i.i.d. data","authors":"Davide GiraudoIRMA","doi":"arxiv-2409.11737","DOIUrl":"https://doi.org/arxiv-2409.11737","url":null,"abstract":"In this paper, we establish an exponential inequality for U-statistics of\u0000i.i.d. data, varying kernel and taking values in a separable Hilbert space. The\u0000bound are expressed as a sum of an exponential term plus an other one involving\u0000the tail of a sum of squared norms. We start by the degenerate case. Then we\u0000provide applications to U-statistics of not necessarily degenerate fixed\u0000kernel, weighted U-statistics and incomplete U-statistics.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Incremental effects for continuous exposures 连续暴露的递增效应
Pub Date : 2024-09-18 DOI: arxiv-2409.11967
Kyle Schindl, Shuying Shen, Edward H. Kennedy
Causal inference problems often involve continuous treatments, such as dose,duration, or frequency. However, continuous exposures bring many challenges,both with identification and estimation. For example, identifying standarddose-response estimands requires that everyone has some chance of receiving anyparticular level of the exposure (i.e., positivity). In this work, we explorean alternative approach: rather than estimating dose-response curves, weconsider stochastic interventions based on exponentially tilting the treatmentdistribution by some parameter $delta$, which we term an incremental effect.This increases or decreases the likelihood a unit receives a given treatmentlevel, and crucially, does not require positivity for identification. We beginby deriving the efficient influence function and semiparametric efficiencybound for these incremental effects under continuous exposures. We then showthat estimation of the incremental effect is dependent on the size of theexponential tilt, as measured by $delta$. In particular, we derive new minimaxlower bounds illustrating how the best possible root mean squared error scaleswith an effective sample size of $n/delta$, instead of usual sample size $n$.Further, we establish new convergence rates and bounds on the bias of doublemachine learning-style estimators. Our novel analysis gives a better dependenceon $delta$ compared to standard analyses, by using mixed supremum and $L_2$norms, instead of just $L_2$ norms from Cauchy-Schwarz bounds. Finally, we showthat taking $delta to infty$ gives a new estimator of the dose-responsecurve at the edge of the support, and we give a detailed study of convergencerates in this regime.
因果推断问题通常涉及连续的处理,如剂量、持续时间或频率。然而,连续暴露给识别和估计带来了许多挑战。例如,识别标准剂量-反应估计值要求每个人都有一定的机会接受任何特定水平的暴露(即阳性)。在这项工作中,我们探索了另一种方法:与其估计剂量-反应曲线,不如考虑随机干预,即通过某个参数$delta$对治疗分布进行指数倾斜,我们称之为增量效应。我们首先推导出连续暴露下这些增量效应的有效影响函数和半参数效率边界。然后,我们证明增量效应的估计取决于指数倾斜的大小,以 $delta$ 衡量。特别是,我们推导出了新的最小下限,说明了最佳均方根误差是如何与有效样本量 $n/delta$ 而不是通常样本量 $n$ 成比例的。与标准分析相比,我们的新分析通过使用混合至上和 $L_2$ 准则,而不仅仅是考奇-施瓦茨边界中的 $L_2$ 准则,给出了对 $delta$ 的更好依赖性。最后,我们证明了将 $delta to infty$取值会在支持边缘给出一个新的剂量-反应曲线估计值,我们还对这一机制中的收敛因子进行了详细研究。
{"title":"Incremental effects for continuous exposures","authors":"Kyle Schindl, Shuying Shen, Edward H. Kennedy","doi":"arxiv-2409.11967","DOIUrl":"https://doi.org/arxiv-2409.11967","url":null,"abstract":"Causal inference problems often involve continuous treatments, such as dose,\u0000duration, or frequency. However, continuous exposures bring many challenges,\u0000both with identification and estimation. For example, identifying standard\u0000dose-response estimands requires that everyone has some chance of receiving any\u0000particular level of the exposure (i.e., positivity). In this work, we explore\u0000an alternative approach: rather than estimating dose-response curves, we\u0000consider stochastic interventions based on exponentially tilting the treatment\u0000distribution by some parameter $delta$, which we term an incremental effect.\u0000This increases or decreases the likelihood a unit receives a given treatment\u0000level, and crucially, does not require positivity for identification. We begin\u0000by deriving the efficient influence function and semiparametric efficiency\u0000bound for these incremental effects under continuous exposures. We then show\u0000that estimation of the incremental effect is dependent on the size of the\u0000exponential tilt, as measured by $delta$. In particular, we derive new minimax\u0000lower bounds illustrating how the best possible root mean squared error scales\u0000with an effective sample size of $n/delta$, instead of usual sample size $n$.\u0000Further, we establish new convergence rates and bounds on the bias of double\u0000machine learning-style estimators. Our novel analysis gives a better dependence\u0000on $delta$ compared to standard analyses, by using mixed supremum and $L_2$\u0000norms, instead of just $L_2$ norms from Cauchy-Schwarz bounds. Finally, we show\u0000that taking $delta to infty$ gives a new estimator of the dose-response\u0000curve at the edge of the support, and we give a detailed study of convergence\u0000rates in this regime.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Cyclicity Analysis of the Ornstein-Uhlenbeck Process 奥恩斯坦-乌伦贝克过程的周期性分析
Pub Date : 2024-09-18 DOI: arxiv-2409.12102
Vivek Kaushik
In this thesis, we consider an $N$-dimensional Ornstein-Uhlenbeck (OU)process satisfying the linear stochastic differential equation $dmathbf x(t) =- mathbf Bmathbf x(t) dt + boldsymbol Sigma d mathbf w(t).$ Here, $mathbfB$ is a fixed $N times N$ circulant friction matrix whose eigenvalues havepositive real parts, $boldsymbol Sigma$ is a fixed $N times M$ matrix. Weconsider a signal propagation model governed by this OU process. In this model,an underlying signal propagates throughout a network consisting of $N$ linkedsensors located in space. We interpret the $n$-th component of the OU processas the measurement of the propagating effect made by the $n$-th sensor. Thematrix $mathbf B$ represents the sensor network structure: if $mathbf B$ hasfirst row $(b_1 , dots , b_N),$ where $b_1>0$ and $b_2 , dots , b_N le 0,$ then the magnitude of $b_p$ quantifies how receptive the $n$-thsensor is to activity within the $(n+p-1)$-th sensor. Finally, the $(m,n)$-thentry of the matrix $mathbf D = frac{boldsymbol Sigma boldsymbolSigma^text T}{2}$ is the covariance of the component noises injected into the$m$-th and $n$-th sensors. For different choices of $mathbf B$ and$boldsymbol Sigma,$ we investigate whether Cyclicity Analysis enables us torecover the structure of network. Roughly speaking, Cyclicity Analysis studiesthe lead-lag dynamics pertaining to the components of a multivariate signal. Wespecifically consider an $N times N$ skew-symmetric matrix $mathbf Q,$ knownas the lead matrix, in which the sign of its $(m,n)$-th entry captures thelead-lag relationship between the $m$-th and $n$-th component OU processes. Weinvestigate whether the structure of the leading eigenvector of $mathbf Q,$the eigenvector corresponding to the largest eigenvalue of $mathbf Q$ inmodulus, reflects the network structure induced by $mathbf B.$
在本论文中,我们考虑一个 $N$ 维的奥恩斯坦-乌伦贝克(OU)过程,该过程满足线性随机微分方程 $dmathbf x(t) =- mathbf Bmathbf x(t) dt + boldsymbol Sigma d mathbf w(t)。这里,$mathbfB$是一个固定的$N times N$环形摩擦矩阵,其特征值的实部为正,$boldsymbol Sigma$是一个固定的$N times M$矩阵。我们将考虑一个受此 OU 过程控制的信号传播模型。在这个模型中,一个基本信号在由位于空间的 $N$ 链接传感器组成的网络中传播。我们将 OU 过程的第 n 个分量解释为第 n 个传感器对传播效果的测量。矩阵 $mathbf B$ 表示传感器网络结构:如果 $mathbf B$ 的第一行为 $(b_1 , dots , b_N), $ 其中 $b_1>0$ 并且 $b_2 , dots , b_N le 0, $ 那么 $b_p$ 的大小量化了 $n$-th 传感器对 $(n+p-1)$-th 传感器内活动的接受程度。最后,矩阵 $mathbf D = frac{boldsymbol Sigma Sigma^text T}{2}$ 的 $(m,n)$ 条目是注入 $m$-th 和 $n$-th 传感器的分量噪声的协方差。对于 $mathbf B$ 和 $boldsymbol Sigma$ 的不同选择,我们研究了循环分析是否能让我们恢复网络结构。粗略地说,循环分析研究的是多变量信号成分的前导-滞后动态。我们特别考虑了一个 $N times N$ 的倾斜对称矩阵 $/mathbf Q,$ 称为先导矩阵,其中 $(m,n)$-th 条目的符号捕捉了 $m$-th 和 $n$-th 分量 OU 过程之间的先导-滞后关系。我们研究了$mathbf Q的前导特征向量的结构,即对应于$mathbf Q的最大特征值的特征向量,是否反映了$mathbf B所诱导的网络结构。
{"title":"Cyclicity Analysis of the Ornstein-Uhlenbeck Process","authors":"Vivek Kaushik","doi":"arxiv-2409.12102","DOIUrl":"https://doi.org/arxiv-2409.12102","url":null,"abstract":"In this thesis, we consider an $N$-dimensional Ornstein-Uhlenbeck (OU)\u0000process satisfying the linear stochastic differential equation $dmathbf x(t) =\u0000- mathbf Bmathbf x(t) dt + boldsymbol Sigma d mathbf w(t).$ Here, $mathbf\u0000B$ is a fixed $N times N$ circulant friction matrix whose eigenvalues have\u0000positive real parts, $boldsymbol Sigma$ is a fixed $N times M$ matrix. We\u0000consider a signal propagation model governed by this OU process. In this model,\u0000an underlying signal propagates throughout a network consisting of $N$ linked\u0000sensors located in space. We interpret the $n$-th component of the OU process\u0000as the measurement of the propagating effect made by the $n$-th sensor. The\u0000matrix $mathbf B$ represents the sensor network structure: if $mathbf B$ has\u0000first row $(b_1 , dots , b_N),$ where $b_1>0$ and $b_2 , dots \u0000, b_N le 0,$ then the magnitude of $b_p$ quantifies how receptive the $n$-th\u0000sensor is to activity within the $(n+p-1)$-th sensor. Finally, the $(m,n)$-th\u0000entry of the matrix $mathbf D = frac{boldsymbol Sigma boldsymbol\u0000Sigma^text T}{2}$ is the covariance of the component noises injected into the\u0000$m$-th and $n$-th sensors. For different choices of $mathbf B$ and\u0000$boldsymbol Sigma,$ we investigate whether Cyclicity Analysis enables us to\u0000recover the structure of network. Roughly speaking, Cyclicity Analysis studies\u0000the lead-lag dynamics pertaining to the components of a multivariate signal. We\u0000specifically consider an $N times N$ skew-symmetric matrix $mathbf Q,$ known\u0000as the lead matrix, in which the sign of its $(m,n)$-th entry captures the\u0000lead-lag relationship between the $m$-th and $n$-th component OU processes. We\u0000investigate whether the structure of the leading eigenvector of $mathbf Q,$\u0000the eigenvector corresponding to the largest eigenvalue of $mathbf Q$ in\u0000modulus, reflects the network structure induced by $mathbf B.$","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Linear hypothesis testing in high-dimensional heteroscedastics via random integration 通过随机积分在高维异序中进行线性假设检验
Pub Date : 2024-09-18 DOI: arxiv-2409.12066
Mingxiang Cao, Hongwei Zhang, Kai Xu, Daojiang He
In this paper, for the problem of heteroskedastic general linear hypothesistesting (GLHT) in high-dimensional settings, we propose a random integrationmethod based on the reference L2-norm to deal with such problems. Theasymptotic properties of the test statistic can be obtained under the nullhypothesis when the relationship between data dimensions and sample size is notspecified. The results show that it is more advisable to approximate the nulldistribution of the test using the distribution of the chi-square type mixture,and it is shown through some numerical simulations and real data analysis thatour proposed test is powerful.
本文针对高维环境下的异方差一般线性假设检验(GLHT)问题,提出了一种基于参考 L2 正态的随机积分法来处理此类问题。当数据维度和样本量之间的关系未被指定时,可以在零假设下获得检验统计量的渐近性质。结果表明,使用秩方类型混合物的分布来近似检验的无分布是更可取的,并通过一些数值模拟和实际数据分析证明了我们提出的检验是强大的。
{"title":"Linear hypothesis testing in high-dimensional heteroscedastics via random integration","authors":"Mingxiang Cao, Hongwei Zhang, Kai Xu, Daojiang He","doi":"arxiv-2409.12066","DOIUrl":"https://doi.org/arxiv-2409.12066","url":null,"abstract":"In this paper, for the problem of heteroskedastic general linear hypothesis\u0000testing (GLHT) in high-dimensional settings, we propose a random integration\u0000method based on the reference L2-norm to deal with such problems. The\u0000asymptotic properties of the test statistic can be obtained under the null\u0000hypothesis when the relationship between data dimensions and sample size is not\u0000specified. The results show that it is more advisable to approximate the null\u0000distribution of the test using the distribution of the chi-square type mixture,\u0000and it is shown through some numerical simulations and real data analysis that\u0000our proposed test is powerful.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Sparse Factor Analysis for Categorical Data with the Group-Sparse Generalized Singular Value Decomposition 利用组-解析广义奇异值分解对分类数据进行稀疏因子分析
Pub Date : 2024-09-18 DOI: arxiv-2409.11789
Ju-Chi YuCAMH, Julie Le BorgneRID-AGE, CHRU Lille, Anjali KrishnanCUNY, Arnaud GloaguenCNRGH, JACOB, Cheng-Ta YangNCKU, Laura A RabinCUNY, Hervé AbdiUT Dallas, Vincent Guillemot
Correspondence analysis, multiple correspondence analysis and theirdiscriminant counterparts (i.e., discriminant simple correspondence analysisand discriminant multiple correspondence analysis) are methods of choice foranalyzing multivariate categorical data. In these methods, variables areintegrated into optimal components computed as linear combinations whoseweights are obtained from a generalized singular value decomposition (GSVD)that integrates specific metric constraints on the rows and columns of theoriginal data matrix. The weights of the linear combinations are, in turn, usedto interpret the components, and this interpretation is facilitated whencomponents are 1) pairwise orthogonal and 2) when the values of the weights areeither large or small but not intermediate-a pattern called a simple or asparse structure. To obtain such simple configurations, the optimizationproblem solved by the GSVD is extended to include new constraints thatimplement component orthogonality and sparse weights. Because multiplecorrespondence analysis represents qualitative variables by a set of binaryvariables, an additional group constraint is added to the optimization problemin order to sparsify the whole set representing one qualitative variable. Thisnew algorithm-called group-sparse GSVD (gsGSVD)-integrates these constraintsvia an iterative projection scheme onto the intersection of subspaces whereeach subspace implements a specific constraint. In this paper, we expose thisnew algorithm and show how it can be adapted to the sparsification of simpleand multiple correspondence analysis, and illustrate its applications with theanalysis of four different data sets-each illustrating the sparsification of aparticular CA-based analysis.
对应分析、多重对应分析及其对应的判别分析(即判别简单对应分析和判别多重对应分析)是分析多元分类数据的首选方法。在这些方法中,变量被整合为最优成分,计算为线性组合,其权重来自广义奇异值分解(GSVD),该分解整合了原始数据矩阵行和列的特定度量约束。反过来,线性组合的权重也用于解释成分,当成分 1)成对正交,2)权重值或大或小,但不是中间值时,这种解释就会变得容易--这种模式被称为简单或稀疏结构。为了获得这种简单结构,GSVD 所求解的优化问题被扩展到包括新的约束条件,以实现成分正交和权重稀疏。由于多重对应分析用一组二进制变量表示定性变量,因此在优化问题中增加了一个额外的组约束,以稀疏化代表一个定性变量的整个组。这种新算法被称为组稀疏 GSVD(gsGSVD),它通过迭代投影方案将这些约束整合到子空间的交集上,其中每个子空间都实现了特定的约束。在本文中,我们揭示了这种新算法,并展示了它如何适用于简单和多重对应分析的稀疏化,还通过分析四个不同的数据集说明了它的应用--每个数据集都说明了基于 CA 的特定分析的稀疏化。
{"title":"Sparse Factor Analysis for Categorical Data with the Group-Sparse Generalized Singular Value Decomposition","authors":"Ju-Chi YuCAMH, Julie Le BorgneRID-AGE, CHRU Lille, Anjali KrishnanCUNY, Arnaud GloaguenCNRGH, JACOB, Cheng-Ta YangNCKU, Laura A RabinCUNY, Hervé AbdiUT Dallas, Vincent Guillemot","doi":"arxiv-2409.11789","DOIUrl":"https://doi.org/arxiv-2409.11789","url":null,"abstract":"Correspondence analysis, multiple correspondence analysis and their\u0000discriminant counterparts (i.e., discriminant simple correspondence analysis\u0000and discriminant multiple correspondence analysis) are methods of choice for\u0000analyzing multivariate categorical data. In these methods, variables are\u0000integrated into optimal components computed as linear combinations whose\u0000weights are obtained from a generalized singular value decomposition (GSVD)\u0000that integrates specific metric constraints on the rows and columns of the\u0000original data matrix. The weights of the linear combinations are, in turn, used\u0000to interpret the components, and this interpretation is facilitated when\u0000components are 1) pairwise orthogonal and 2) when the values of the weights are\u0000either large or small but not intermediate-a pattern called a simple or a\u0000sparse structure. To obtain such simple configurations, the optimization\u0000problem solved by the GSVD is extended to include new constraints that\u0000implement component orthogonality and sparse weights. Because multiple\u0000correspondence analysis represents qualitative variables by a set of binary\u0000variables, an additional group constraint is added to the optimization problem\u0000in order to sparsify the whole set representing one qualitative variable. This\u0000new algorithm-called group-sparse GSVD (gsGSVD)-integrates these constraints\u0000via an iterative projection scheme onto the intersection of subspaces where\u0000each subspace implements a specific constraint. In this paper, we expose this\u0000new algorithm and show how it can be adapted to the sparsification of simple\u0000and multiple correspondence analysis, and illustrate its applications with the\u0000analysis of four different data sets-each illustrating the sparsification of a\u0000particular CA-based analysis.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Poisson and Gamma Model Marginalisation and Marginal Likelihood calculation using Moment-generating Functions 泊松模型和伽玛模型边际化以及使用时刻生成函数计算边际似然值
Pub Date : 2024-09-17 DOI: arxiv-2409.11167
Siyang Li, David van Dyk, Maximilian Autenrieth
We present a new analytical method to derive the likelihood function that hasthe population of parameters marginalised out in Bayesian hierarchical models.This method is also useful to find the marginal likelihoods in Bayesian modelsor in random-effect linear mixed models. The key to this method is to takehigh-order (sometimes fractional) derivatives of the prior moment-generatingfunction if particular existence and differentiability conditions hold. In particular, this analytical method assumes that the likelihood is eitherPoisson or gamma. Under Poisson likelihoods, the observed Poisson countdetermines the order of the derivative. Under gamma likelihoods, the shapeparameter, which is assumed to be known, determines the order of the fractionalderivative. We also present some examples validating this new analytical method.
我们提出了一种新的分析方法,用于推导贝叶斯层次模型中参数群体边际似然函数。这种方法也适用于贝叶斯模型或随机效应线性混合模型中边际似然的求取。这种方法的关键在于,如果特定的存在性和可微性条件成立,则对先验矩生成函数取高阶(有时是分数)导数。特别是,这种分析方法假定似然是泊松似然或伽马似然。在泊松似然条件下,观测到的泊松计数决定导数的阶数。在伽马似然条件下,假定已知的形状参数决定分数导数的阶次。我们还列举了一些例子来验证这种新的分析方法。
{"title":"Poisson and Gamma Model Marginalisation and Marginal Likelihood calculation using Moment-generating Functions","authors":"Siyang Li, David van Dyk, Maximilian Autenrieth","doi":"arxiv-2409.11167","DOIUrl":"https://doi.org/arxiv-2409.11167","url":null,"abstract":"We present a new analytical method to derive the likelihood function that has\u0000the population of parameters marginalised out in Bayesian hierarchical models.\u0000This method is also useful to find the marginal likelihoods in Bayesian models\u0000or in random-effect linear mixed models. The key to this method is to take\u0000high-order (sometimes fractional) derivatives of the prior moment-generating\u0000function if particular existence and differentiability conditions hold. In particular, this analytical method assumes that the likelihood is either\u0000Poisson or gamma. Under Poisson likelihoods, the observed Poisson count\u0000determines the order of the derivative. Under gamma likelihoods, the shape\u0000parameter, which is assumed to be known, determines the order of the fractional\u0000derivative. We also present some examples validating this new analytical method.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Edge spectra of Gaussian random symmetric matrices with correlated entries 具有相关条目的高斯随机对称矩阵的边缘谱
Pub Date : 2024-09-17 DOI: arxiv-2409.11381
Debapratim Banerjee, Soumendu Sundar Mukherjee, Dipranjan Pal
We study the largest eigenvalue of a Gaussian random symmetric matrix $X_n$,with zero-mean, unit variance entries satisfying the condition $sup_{(i, j)ne (i', j')}|mathbb{E}[X_{ij} X_{i'j'}]| = O(n^{-(1 + varepsilon)})$, where$varepsilon > 0$. It follows from Catalano et al. (2024) that the empiricalspectral distribution of $n^{-1/2} X_n$ converges weakly almost surely to thestandard semi-circle law. Using a F"{u}redi-Koml'{o}s-type high momentanalysis, we show that the largest eigenvalue $lambda_1(n^{-1/2} X_n)$ of$n^{-1/2} X_n$ converges almost surely to $2$. This result is essentiallyoptimal in the sense that one cannot take $varepsilon = 0$ and still obtain analmost sure limit of $2$. We also derive Gaussian fluctuation results for thelargest eigenvalue in the case where the entries have a common non-zero mean.Let $Y_n = X_n + frac{lambda}{sqrt{n}}mathbf{1} mathbf{1}^top$. When$varepsilon ge 1$ and $lambda gg n^{1/4}$, we show that [ n^{1/2}bigg(lambda_1(n^{-1/2} Y_n) - lambda - frac{1}{lambda}bigg)xrightarrow{d} sqrt{2} Z, ] where $Z$ is a standard Gaussian. On the otherhand, when $0 < varepsilon < 1$, we have $mathrm{Var}(frac{1}{n}sum_{i,j}X_{ij}) = O(n^{1 - varepsilon})$. Assuming that$mathrm{Var}(frac{1}{n}sum_{i, j} X_{ij}) = sigma^2 n^{1 - varepsilon} (1+ o(1))$, if $lambda gg n^{varepsilon/4}$, then we have [ n^{varepsilon/2}bigg(lambda_1(n^{-1/2} Y_n) - lambda -frac{1}{lambda}bigg) xrightarrow{d} sigma Z. ] While the ranges of$lambda$ in these fluctuation results are certainly not optimal, a strikingaspect is that different scalings are required in the two regimes $0 <varepsilon < 1$ and $varepsilon ge 1$.
我们研究了一个高斯随机对称矩阵 $X_n$的最大特征值,该矩阵具有零均值、单位方差条目,满足条件 $sup_{(i, j)ne (i', j')}|mathbb{E}[X_{ij} X_{i'j'}]| = O(n^{-(1+varepsilon)})$,其中$varepsilon > 0$。根据 Catalano 等人(2024 年)的研究,$n^{-1/2} X_n$ 的经验谱分布几乎肯定弱收敛于标准半圆律。利用 F"{u}redi-Koml'{o}s-type high momentanalysis,我们证明了 $n^{-1/2} X_n$ 的最大特征值 $lambda_1(n^{-1/2} X_n)$几乎肯定收敛于 $2$。这一结果本质上是最优的,因为我们不可能取 $varepsilon = 0$ 并仍然得到几乎确定的 2$ 极限。让 $Y_n = X_n + frac{lambda}{sqrt{n}}mathbf{1}.mathbf{1}^top$.当$varepsilon为1且$lambda为n^{1/4}时,我们证明了([ n^{1/2}bigg(lambda_1(n^{-1/2} Y_n) -lambda -frac{1}lambda}bigg)xrightarrow{d}sqrt{2}Z, ] 其中 $Z$ 是标准高斯。另一方面,当 $0 < varepsilon < 1 时,我们有 $mathrm{Var}(frac{1}{n}sum_{i,j}X_{ij}) = O(n^{1 - varepsilon})$。假设$mathrm{Var}(frac{1}{n}sum_{i,j} X_{ij}) = sigma^2 n^{1 - varepsilon} (1+ o(1))$、如果 $lambda gg n^{varepsilon/4}$,那么我们就有[ n^{varepsilon/2}bigg(lambda_1(n^{-1/2} Y_n) -lambda -frac{1}{lambda}bigg)xrightarrow{d}sigma Z.]虽然这些波动结果中的$lambda$范围肯定不是最优的,但一个显著的方面是,在$0
{"title":"Edge spectra of Gaussian random symmetric matrices with correlated entries","authors":"Debapratim Banerjee, Soumendu Sundar Mukherjee, Dipranjan Pal","doi":"arxiv-2409.11381","DOIUrl":"https://doi.org/arxiv-2409.11381","url":null,"abstract":"We study the largest eigenvalue of a Gaussian random symmetric matrix $X_n$,\u0000with zero-mean, unit variance entries satisfying the condition $sup_{(i, j)\u0000ne (i', j')}|mathbb{E}[X_{ij} X_{i'j'}]| = O(n^{-(1 + varepsilon)})$, where\u0000$varepsilon > 0$. It follows from Catalano et al. (2024) that the empirical\u0000spectral distribution of $n^{-1/2} X_n$ converges weakly almost surely to the\u0000standard semi-circle law. Using a F\"{u}redi-Koml'{o}s-type high moment\u0000analysis, we show that the largest eigenvalue $lambda_1(n^{-1/2} X_n)$ of\u0000$n^{-1/2} X_n$ converges almost surely to $2$. This result is essentially\u0000optimal in the sense that one cannot take $varepsilon = 0$ and still obtain an\u0000almost sure limit of $2$. We also derive Gaussian fluctuation results for the\u0000largest eigenvalue in the case where the entries have a common non-zero mean.\u0000Let $Y_n = X_n + frac{lambda}{sqrt{n}}mathbf{1} mathbf{1}^top$. When\u0000$varepsilon ge 1$ and $lambda gg n^{1/4}$, we show that [ n^{1/2}bigg(lambda_1(n^{-1/2} Y_n) - lambda - frac{1}{lambda}bigg)\u0000xrightarrow{d} sqrt{2} Z, ] where $Z$ is a standard Gaussian. On the other\u0000hand, when $0 < varepsilon < 1$, we have $mathrm{Var}(frac{1}{n}sum_{i,\u0000j}X_{ij}) = O(n^{1 - varepsilon})$. Assuming that\u0000$mathrm{Var}(frac{1}{n}sum_{i, j} X_{ij}) = sigma^2 n^{1 - varepsilon} (1\u0000+ o(1))$, if $lambda gg n^{varepsilon/4}$, then we have [ n^{varepsilon/2}bigg(lambda_1(n^{-1/2} Y_n) - lambda -\u0000frac{1}{lambda}bigg) xrightarrow{d} sigma Z. ] While the ranges of\u0000$lambda$ in these fluctuation results are certainly not optimal, a striking\u0000aspect is that different scalings are required in the two regimes $0 <\u0000varepsilon < 1$ and $varepsilon ge 1$.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Large Deviations Principle for Bures-Wasserstein Barycenters 布雷斯-瓦塞尔斯坦原点的大偏差原理
Pub Date : 2024-09-17 DOI: arxiv-2409.11384
Adam Quinn Jaffe, Leonardo V. Santoro
We prove the large deviations principle for empirical Bures-Wassersteinbarycenters of independent, identically-distributed samples of covariancematrices and covariance operators. As an application, we explore someconsequences of our results for the phenomenon of dimension-free concentrationof measure for Bures-Wasserstein barycenters. Our theory reveals a novel notionof exponential tilting in the Bures-Wasserstein space, which, in analogy withCr'amer's theorem in the Euclidean case, solves the relative entropyprojection problem under a constraint on the barycenter. Notably, this methodof proof is easy to adapt to other geometric settings of interest; with thesame method, we obtain large deviations principles for empirical barycenters inRiemannian manifolds and the univariate Wasserstein space, and we obtain largedeviations upper bounds for empirical barycenters in the general multivariateWasserstein space. In fact, our results are the first known large deviationsprinciples for Fr'echet means in any non-linear metric space.
我们证明了独立、同分布样本协方差矩阵和协方差算子的经验布雷斯-瓦瑟斯坦双中心的大偏差原理。作为一种应用,我们探讨了我们的结果对布雷斯-瓦瑟斯坦副中心无维度度量集中现象的一些影响。我们的理论揭示了布雷斯-瓦瑟斯坦空间中指数倾斜的新概念,与欧几里得情况下的卡梅尔定理类似,它解决了在原点约束下的相对熵投影问题。值得注意的是,这种证明方法很容易适用于其他感兴趣的几何环境;用同样的方法,我们得到了黎曼流形和单变量瓦瑟斯坦空间中经验原点的大偏差原理,并得到了一般多变量瓦瑟斯坦空间中经验原点的大偏差上界。事实上,我们的结果是第一个已知的非线性度量空间中 Fr'echet 均值的大偏差原理。
{"title":"Large Deviations Principle for Bures-Wasserstein Barycenters","authors":"Adam Quinn Jaffe, Leonardo V. Santoro","doi":"arxiv-2409.11384","DOIUrl":"https://doi.org/arxiv-2409.11384","url":null,"abstract":"We prove the large deviations principle for empirical Bures-Wasserstein\u0000barycenters of independent, identically-distributed samples of covariance\u0000matrices and covariance operators. As an application, we explore some\u0000consequences of our results for the phenomenon of dimension-free concentration\u0000of measure for Bures-Wasserstein barycenters. Our theory reveals a novel notion\u0000of exponential tilting in the Bures-Wasserstein space, which, in analogy with\u0000Cr'amer's theorem in the Euclidean case, solves the relative entropy\u0000projection problem under a constraint on the barycenter. Notably, this method\u0000of proof is easy to adapt to other geometric settings of interest; with the\u0000same method, we obtain large deviations principles for empirical barycenters in\u0000Riemannian manifolds and the univariate Wasserstein space, and we obtain large\u0000deviations upper bounds for empirical barycenters in the general multivariate\u0000Wasserstein space. In fact, our results are the first known large deviations\u0000principles for Fr'echet means in any non-linear metric space.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"102 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Valid Credible Ellipsoids for Linear Functionals by a Renormalized Bernstein-von Mises Theorem 通过重规范化伯恩斯坦-冯-米塞斯定理实现线性函数的有效可信椭圆形
Pub Date : 2024-09-17 DOI: arxiv-2409.10947
Gustav Rømer
We consider a semi-parametric Gaussian regression model, equipped with ahigh-dimensional Gaussian prior. We address the frequentist validity ofposterior credible sets for a vector of linear functionals. We specify conditions for a 'renormalized' Bernstein-von Mises theorem (BvM),where the posterior, centered at its mean, and the posterior mean, centered atthe ground truth, have the same normal approximation. This requires neither asolution to the information equation nor a $sqrt{N}$-consistent estimator. We show that our renormalized BvM implies that a credible ellipsoid,specified by the mean and variance of the posterior, is an asymptoticconfidence set. For a single linear functional, we identify such a credibleellipsoid with a symmetric credible interval around the posterior mean. Webound the diameter. We check the conditions for Darcy's problem, where the information equationhas no solution in natural settings. For the Schr"odinger problem, we recoveran efficient semi-parametric BvM from our renormalized BvM.
我们考虑了一个半参数高斯回归模型,该模型配备了一个高维高斯先验。我们探讨了线性函数向量的后验可信集的常量有效性。我们明确了 "重归一化 "伯恩斯坦-冯-米塞斯定理(BvM)的条件,即以其均值为中心的后验均值和以地面实况为中心的后验均值具有相同的正态近似值。这既不需要对信息方程求解,也不需要$sqrt{N}$一致的估计器。我们证明,我们的重归一化 BvM 意味着由后验均值和方差指定的可信椭圆是一个渐近可信集。对于单一线性函数,我们将这样一个可信椭圆与后验均值周围的对称可信区间联系起来。确定直径我们检验了达西问题的条件,在达西问题中,信息方程在自然环境下没有解。对于薛定谔问题,我们从重新规范化的 BvM 中恢复了一个高效的半参数 BvM。
{"title":"Valid Credible Ellipsoids for Linear Functionals by a Renormalized Bernstein-von Mises Theorem","authors":"Gustav Rømer","doi":"arxiv-2409.10947","DOIUrl":"https://doi.org/arxiv-2409.10947","url":null,"abstract":"We consider a semi-parametric Gaussian regression model, equipped with a\u0000high-dimensional Gaussian prior. We address the frequentist validity of\u0000posterior credible sets for a vector of linear functionals. We specify conditions for a 'renormalized' Bernstein-von Mises theorem (BvM),\u0000where the posterior, centered at its mean, and the posterior mean, centered at\u0000the ground truth, have the same normal approximation. This requires neither a\u0000solution to the information equation nor a $sqrt{N}$-consistent estimator. We show that our renormalized BvM implies that a credible ellipsoid,\u0000specified by the mean and variance of the posterior, is an asymptotic\u0000confidence set. For a single linear functional, we identify such a credible\u0000ellipsoid with a symmetric credible interval around the posterior mean. We\u0000bound the diameter. We check the conditions for Darcy's problem, where the information equation\u0000has no solution in natural settings. For the Schr\"odinger problem, we recover\u0000an efficient semi-parametric BvM from our renormalized BvM.","PeriodicalId":501379,"journal":{"name":"arXiv - STAT - Statistics Theory","volume":"119 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
arXiv - STAT - Statistics Theory
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1