An official website of the United States government
ABSTRACT In modern statistical applications, identifying critical features in high‐dimensional data is essential for scientific discoveries. Traditional best subset selection methods face computational challenges, while regularization approaches such as Lasso, SCAD and their variants often exhibit poor performance with ultrahigh‐dimensional data. Sure screening methods, widely used for dimensionality reduction, have been developed as popular alternatives, but few target heavy‐tailed characteristics in modern big data. This paper introduces a new sure screening method, based on robust distance correlation (‘RDC’), designed for heavy‐tailed data. The proposed method inherits the benefits of the original model‐free distance correlation‐based screening while robustly estimating distance correlation in the presence of heavy‐tailed data. We further develop an FDR control procedure by incorporating the Reflection via Data Splitting (REDS) method. Extensive simulations demonstrate the method's advantage over existing screening procedures under different scenarios of heavy‐tailedness. Its application to high‐dimensional heavy‐tailed RNA‐seq data from The Cancer Genome Atlas (TCGA) pancreatic cancer cohort showcases superior performance in identifying biologically meaningful genes predictive of MAPK1 protein expression critical to pancreatic cancer.
more »
« less
Homogeneity Structure Learning in Large-scale Panel Data with Heavy-tailed Errors
Large-scale panel data is ubiquitous in many modern data science applications. Conventional panel data analysis methods fail to address the new challenges, like individual impacts of covariates, endogeneity, embedded low-dimensional structure, and heavy-tailed errors, arising from the innovation of data collection platforms on which applications operate. In response to these challenges, this paper studies large-scale panel data with an interactive effects model. This model takes into account the individual impacts of covariates on each spatial node and removes the exogenous condition by allowing latent factors to affect both covariates and errors. Besides, we waive the sub-Gaussian assumption and allow the errors to be heavy-tailed. Further, we propose a data-driven procedure to learn a parsimonious yet flexible homogeneity structure embedded in high-dimensional individual impacts of covariates. The homogeneity structure assumes that there exists a partition of regression coeffcients where the coeffcients are the same within each group but different between the groups. The homogeneity structure is flexible as it contains many widely assumed low dimensional structures (sparsity, global impact, etc.) as its special cases. Non-asymptotic properties are established to justify the proposed learning procedure. Extensive numerical experiments demonstrate the advantage of the proposed learning procedure over conventional methods especially when the data are generated from heavy-tailed distributions.
more »
« less
- PAR ID:
- 10217339
- Date Published:
- Journal Name:
- Journal of machine learning research
- Volume:
- 22
- ISSN:
- 1533-7928
- Page Range / eLocation ID:
- 1-42
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Expected shortfall (ES), also known as superquantile or conditional value-at-risk, is an important measure in risk analysis and stochastic optimisation and has applications beyond these fields. In finance, it refers to the conditional expected return of an asset given that the return is below some quantile of its distribution. In this paper, we consider a joint regression framework recently proposed to model the quantile and ES of a response variable simultaneously, given a set of covariates. The current state-of-the-art approach to this problem involves minimising a non-differentiable and non-convex joint loss function, which poses numerical challenges and limits its applicability to large-scale data. Motivated by the idea of using Neyman-orthogonal scores to reduce sensitivity to nuisance parameters, we propose a statistically robust and computationally efficient two-step procedure for fitting joint quantile and ES regression models that can handle highly skewed and heavy-tailed data. We establish explicit non-asymptotic bounds on estimation and Gaussian approximation errors that lay the foundation for statistical inference, even with increasing covariate dimensions. Finally, through numerical experiments and two data applications, we demonstrate that our approach well balances robustness, statistical, and numerical efficiencies for expected shortfall regression.more » « less
-
We study high-dimensional signal recovery from non-linear measurements with design vectors having elliptically symmetric distribution. Special attention is devoted to the situation when the unknown signal belongs to a set of low statistical complexity, while both the measurements and the design vectors are heavy-tailed. We propose and analyze a new estimator that adapts to the structure of the problem, while being robust both to the possible model misspecification characterized by arbitrary non-linearity of the measurements as well as to data corruption modeled by the heavy-tailed distributions. Moreover, this estimator has low computational complexity. Our results are expressed in the form of exponential concentration inequalities for the error of the proposed estimator. On the technical side, our proofs rely on the generic chaining methods, and illustrate the power of this approach for statistical applications. Theory is supported by numerical experiments demonstrating that our estimator outperforms existing alternatives when data is heavy-tailed.more » « less
-
Representation learning in high-dimensional spaces faces significant robustness challenges with noisy inputs, particularly with heavy-tailed noise. Arguing that topological data analysis (TDA) offers a solution, we leverage TDA to enhance representation stability in neural networks. Our theoretical analysis establishes conditions under which incorporating topological summaries improves robustness to input noise, especially for heavy-tailed distributions. Extending these results to representation-balancing methods used in causal inference, we propose the *Topology-Aware Treatment Effect Estimation* (TATEE) framework, through which we demonstrate how topological awareness can lead to learning more robust representations. A key advantage of this approach is that it requires no ground-truth or validation data, making it suitable for observational settings common in causal inference. The method remains computationally efficient with overhead scaling linearly with data size while staying constant in input dimension. Through extensive experiments with -stable noise distributions, we validate our theoretical results, demonstrating that TATEE consistently outperforms existing methods across noise regimes. This work extends stability properties of topological summaries to representation learning via a tractable framework scalable for high-dimensional inputs, providing insights into how it can enhance robustness, with applications extending to domains facing challenges with noisy data, such as causal inference.more » « less
-
Zhang, Aidong; Rangwala, Huzefa (Ed.)Zero-inflated, heavy-tailed spatiotemporal data is common across science and engineering, from climate science to meteorology and seismology. A central modeling objective in such settings is to forecast the intensity, frequency, and timing of extreme and non-extreme events; yet in the context of deep learning, this objective presents several key challenges. First, a deep learning framework applied to such data must unify a mixture of distributions characterizing the zero events, moderate events, and extreme events. Second, the framework must be capable of enforcing parameter constraints across each component of the mixture distribution. Finally, the framework must be flexible enough to accommodate for any changes in the threshold used to define an extreme event after training. To address these challenges, we propose Deep Extreme Mixture Model (DEMM), fusing a deep learning-based hurdle model with extreme value theory to enable point and distribution prediction of zero-inflated, heavy-tailed spatiotemporal variables. The framework enables users to dynamically set a threshold for defining extreme events at inference-time without the need for retraining. We present an extensive experimental analysis applying DEMM to precipitation forecasting, and observe significant improvements in point and distribution prediction. All code is available at https://github.com/andrewmcdonald27/DeepExtremeMixtureModel.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
