Inference for high-dimensional exchangeable arrays
We consider inference for high-dimensional separately and jointly exchangeable arrays where the dimensions may be much larger than the sample sizes. For both exchangeable arrays, we first derive high-dimensional central limit theorems over the rectangles and subsequently develop novel multiplier bootstraps with theoretical guarantees. These theoretical results rely on new technical tools such as Hoeffding-type decomposition and maximal inequalities for the degenerate components in the Hoeffiding-type decomposition for the exchangeable arrays. We exhibit applications of our methods to uniform confidence bands for density estimation under joint exchangeability and penalty choice for $\ell_1$-penalized regression under separate exchangeability. Extensive simulations demonstrate precise uniform coverage rates. We illustrate by constructing uniform confidence bands for international trade network densities.
Code (0)
등록된 구현이 없습니다.
Tasks
Density EstimationregressionVocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
DinTucker: Scaling up Gaussian process models on multidimensional arrays with billions of elements
Infinite Tucker Decomposition (InfTucker) and random function prior models, as nonparametric Bayesian models on infinite exchangeable arrays, are more powerful models than widely-used multilinear factorization methods in…
Tensor DecompositionVariational InferenceThe Mondrian Process
We describe a novel stochastic process that can be used to construct a multidimensional generalization of the stick-breaking process and which is related to the classic stick breaking process described by Sethuraman1994 …
Maximal Inequalities for Separately Exchangeable Empirical Processes
This paper derives new maximal inequalities for empirical processes associated with separately exchangeable random arrays. For fixed index dimension $K\ge 1$, we establish a global maximal inequality bounding the $q$-th …
Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures
The natural habitat of most Bayesian methods is data represented by exchangeable sequences of observations, for which de Finetti's theorem provides the theoretical foundation. Dirichlet process clustering, Gaussian proce…
ClusteringCollaborative FilteringLink PredictionA Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
An explosion of high-throughput DNA sequencing in the past decade has led to a surge of interest in population-scale inference with whole-genome data. Recent work in population genetics has centered on designing inferenc…