论文检索

深层马蹄高斯过程AI 解读

Deep Gaussian processes have recently been proposed as natural objects to fit, similarly to deep neural networks, possibly complex features present in modern data samples, such as compositional structures. Adopting a Bayesian nonparametric approach, it is natural to use deep Gaussian processes as prior distributions, and use the corresponding posterior distributions for statistical inference. We introduce the deep Horseshoe Gaussian process Deep–HGP, a new simple prior based…

函数型图形套索AI 解读

We consider the problem of recovering conditional independence relationships between p jointly distributed Hilbertian random elements given n realizations thereof. We operate in the sparse high-dimensional regime, where n ≪ p and no element is related to more than d ≪ p other elements. In this context, we propose an infinite-dimensional generalization of the graphical lasso. We prove model selection consistency under natural assumptions and extend many classical results to…

一般一阶方法的逐坐标动态与普适性AI 解读

General first-order methods (GFOMs), including many variants of gradient descent and approximate message passing algorithms, constitute a broad class of iterative algorithms widely applied in modern statistical learning problems. Some GFOMs also serve as constructive proof devices, iteratively characterizing the empirical distributions of statistical estimators in the asymptotic regime of large system limits for any fixed number of iterations. This paper develops a…

两阶段抽样下核分布回归的改进学习理论AI 解读

The distribution regression problem encompasses many important statistics and machine learning tasks, and arises in a large range of applications. Among various existing approaches to tackle this problem, kernel methods have become a method of choice. Indeed, kernel distribution regression is both computationally favorable, and supported by a recent learning theory. This theory also tackles the two-stage sampling setting, where only samples from the input distributions are…

使用不可靠源数据的稳健迁移学习AI 解读

This paper addresses challenges in robust transfer learning stemming from ambiguity in Bayes classifiers and weak transferable signals between the target and source distribution. We introduce a novel quantity called the ''ambiguity level'' that measures the discrepancy between the target and source regression functions, propose a simple transfer learning procedure, and establish a general theorem that shows how this new quantity is related to the transferability of learning…

预印本版本摘要 · 查看来源

主成分回归的高维渐近性质AI 解读

We study principal components regression (PCR) in an asymptotic high-dimensional regression setting, where the number of data points is proportional to the dimension. We derive exact limiting formulas for the estimation and prediction risks, which depend in a complicated manner on the eigenvalues of the population covariance, the alignment between the population PCs and the true signal, and the number of selected PCs. A key challenge in the high-dimensional setting stems…

采用逐次提取 varimax 旋转的最优传统因子分析AI 解读

Vintage factor analysis is one important type of factor analysis that aims to first find a low-dimensional representation of the original data, and then to seek a rotation such that the rotated low-dimensional representation is scientifically meaningful. The most widely used vintage factor analysis is the Principal Component Analysis (PCA) followed by the varimax rotation. Despite its popularity, little theoretical guarantee can be provided to date mainly because varimax…

低秩随机矩阵特征向量的逐元素高阶分析：偏差校正、Edgeworth 展开与自助法AI 解读

Understanding the distributions of spectral estimators in low-rank random matrix models, also known as signal-plus-noise matrix models, is fundamentally important in various statistical learning problems, including network analysis, matrix denoising and matrix completion. This paper investigates the entrywise eigenvector distributions in a broad range of low-rank signal-plus-noise matrix models by establishing their higher-order accurate stochastic expansions. At a high…

几何与自适应 k 均值聚类的渐近理论AI 解读

We revisit Pollard’s classical result on consistency for k-means clustering in Euclidean space, with a focus on extensions in two directions: first, to problems where the data may come from interesting geometric settings (e.g., Riemannian manifolds, reflexive Banach spaces or the Wasserstein space); second, to problems where some parameters are chosen adaptively from the data (e.g., k-medoids or elbow-method k-means). Toward this end, we provide a general theory, which shows…

论多路主成分分析AI 解读

Multiway data are becoming more and more common. While there are many approaches to extending principal component analysis (PCA) from usual data matrices to these types of data, the conceptual differences from the usual PCA, and their methodological implications remain largely unknown. This work aims to specifically address these questions. Through a careful and rigorous treatment, we provide a better understanding of the operating characteristics of multiway PCA, develop…

“无需”统一重叠的策略学习：悲观原则与广义经验 Bernstein 不等式AI 解读

This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall outcomes for a given population. Existing policy learning methods rely on a uniform overlap assumption, that is, the propensities of exploring all actions for all individual characteristics must be lower bounded; the performance of the…

算法稳定性保证分布无关预测方法的训练条件覆盖AI 解读

In a supervised learning problem, given a predicted value that is the output of some trained model, how can we quantify our uncertainty around this prediction? Distribution-free predictive inference aims to construct prediction intervals around this output, with valid coverage that does not rely on assumptions on the distribution of the data or the nature of the model training algorithm. Existing methods in this area, including conformal prediction and jackknife+, offer…

利用异质数据学习个体最优策略的强化学习AI 解读

Offline reinforcement learning (RL) aims to find optimal policies in dynamic environments in order to maximize the expected total rewards by leveraging pre-collected data. Learning from heterogeneous data is one of the fundamental challenges in offline RL. Traditional methods focus on learning an optimal policy for all individuals with pre-collected data from a single episode or homogeneous batch episodes, and thus, may result in a suboptimal policy for a heterogeneous…

可逆混合 Gibbs 链的谱隙界AI 解读

Hybrid Gibbs samplers represent a prominent class of approximated Gibbs algorithms that utilize Markov chains to approximate conditional distributions, with the Metropolis-within-Gibbs algorithm standing out as a well-known example. Despite their widespread use in both statistical and non-statistical applications, little is known about their convergence properties. This article introduces novel methods for establishing bounds on the convergence rates of certain reversible…

固定与随机协变量下的协方差回归分析AI 解读

Covariance regression analysis is an approach to linking the covariance of responses to a set of explanatory variables X, where X can be a vector, matrix, or tensor. Most of the literature on this topic focuses on the “Fixed-X” setting and treats X as nonrandom. By contrast, treating explanatory variables X as random, namely the “Random-X” setting, is often more realistic in practice. This article aims to fill this gap in the literature on the estimation and model assessment…

中高维协变量下完全随机实验的去偏回归调整AI 解读

Completely randomized experiment is the gold standard for causal inference. When the covariate information for each experimental candidate is available, one typical way is to include them in covariate adjustments for more accurate treatment effect estimation. In this paper, we investigate this problem under the randomization-based framework, i.e., that the covariates and potential outcomes of all experimental candidates are assumed as deterministic quantities and the…

预印本版本摘要 · 查看来源

纵向网络数据的半参数建模与分析AI 解读

We introduce a semiparametric latent space model for analyzing longitudinal network data. The model consists of a static latent space component and a time-varying node-specific baseline component. We develop a semiparametric efficient score equation for the latent space parameter by adjusting for the baseline nuisance component. Estimation is accomplished through a one-step update estimator and an appropriately penalized maximum likelihood estimator. We derive oracle error…

熵型协方差模型AI 解读

In covariance matrix estimation, one of the challenges lies in finding a suitable model and an efficient estimation method. Two commonly used modelling approaches in the literature involve imposing linear restrictions on the covariance matrix or its inverse. Another approach considers linear restrictions on the matrix logarithm of the covariance matrix. In this paper, we present a general framework for linear restrictions on different transformations of the covariance…

信息性抽样下的半参数自适应估计AI 解读

In probability sampling, sampling weights are often used to remove selection bias in the sample. The Horvitz–Thompson estimator is well known to be consistent and asymptotically normally distributed; however, it is not necessarily efficient. This study derives the semiparametric efficiency bound for various target parameters by considering the survey weights as random variables and consequently proposes two semiparametric estimators with working models on the survey weights.…

用于高斯近似的自归一化 Cramér 型中等偏差定理AI 解读

Berry–Esseen type bounds for Gaussian approximation of standardized sums have been extensively studied under exponential type moment conditions. In this paper, a Cramér type moderate deviation theorem is established for self-normalized Gaussian approximation under finite moment conditions. More specifically, let X1,X2,…,Xn be i.i.d. Rp-valued random vectors with zero means. Let Sn,j=∑ i=1nXij and Vn,j2=∑i=1nXij2. We show that if the correlation matrix of X1 is Ip and the…

交叉随机效应广义线性混合模型中最大似然估计量的渐近分布AI 解读

Generalized linear mixed models (GLMM) with crossed random effects is infamously known to present major challenges not only computationally but also theoretically. In fact, to date only consistency of the maximum likelihood estimators (MLE) has been proved for GLMM with crosses random effects. We introduce a new technique in asymptotic analysis built on a second-order Laplace approximation (LA) of a conditional expectation, whose coefficients are carefully evaluated. The LA…

概率密度 L2 范数的自适应估计及相关问题（二）：基于预言方法的上界AI 解读

This is the second part of the research project initiated in Cleanthous, Georgiadis and Lepski (2024a). We deal with the problem of the adaptive estimation of the L2-norm of a probability density on Rd, d≥1, from independent observations. The unknown density is assumed to be uniformly bounded by unknown constant and to belong to the union of balls in the isotropic/anisotropic Nikolskii’s spaces. In Cleanthous, Georgiadis and Lepski (2024a), we have proved that the optimally…

概率密度 L2 范数的自适应估计及相关问题之一：下界AI 解读

We deal with the problem of the adaptive estimation of the L2–norm of a probability density on Rd, d≥1, from independent observations. The unknown density is assumed to be uniformly bounded and to belong to the union of balls in the isotropic/anisotropic Nikolskii’s spaces. We will show that the optimally adaptive estimators over the collection of considered functional classes do no exist. Also, in the framework of an abstract density model we present several generic lower…

强化学习中的平稳性检验与变点检测AI 解读

We consider reinforcement learning (RL) in possibly nonstationary environments. Many existing RL algorithms in the literature rely on the stationarity assumption that requires the state transition and reward functions to be constant over time. However, this assumption is restrictive in practice and is likely to be violated in a number of applications, including traffic signal control, robotics and mobile health. In this paper, we develop a model-free test to assess the…