arXiv subjects

Feiqing Huang

Publications and source records attributed to Feiqing Huang.

8 recordsLinked to original sources

arXiv2026

Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records

We propose a spectral-based, unsupervised representation learning framework to derive low-dimensional embeddings for clinical concepts and patients in rare disease cohorts from electronic health records, where data are high-dimensional but sample sizes are limited. To overcome this challenge, we incorporate a knowledge matrix extracted from a broader population that shares a partially overlapping subspace with the rare-disease cohort. Our method departs from existing approaches by relaxing restrictive one-to-one signal-alignment assumptions between the latent data matrix and knowledge matrix, allowing more flexible and realistic forms of structured sharing. We introduce a novel two-step spectral embedding procedure: first, we identify and remove irrelevant components from the knowledge matrix; then, we apply a projection-based method to separately recover shared and heterogeneous components. Simulations and an analysis of a real-world multiple sclerosis cohort show that the proposed method outperforms competing approaches, particularly in challenging scenarios where shared signals are weak and only partially aligned, as is common in rare-disease data.

stat.ML↗

arXiv2026

ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data

The proliferation of large-scale and structurally complex data has spurred the integration of machine learning methods into statistical modeling. Recurrent neural networks (RNNs), a foundational class of models for time-dependent data, can be viewed as nonlinear extensions of classical autoregressive moving average models. Despite their flexibility and empirical success in machine learning, RNNs often suffer from limited interpretability and slow training, which hinders their use in statistics. This paper proposes the Parallelized RNN (ParaRNN), a novel model composed of multiple small recurrent units. ParaRNN admits an additive representation that decouples recurrent dynamics into interpretable components, whose behavior can be characterized through recurrence features. This interpretability enables its applications in nonparametric regression for time-dependent data, while the design also allows efficient parallelization. The approximation capacity and non-asymptotic prediction error bounds in a nonparametric regression setting are established for ParaRNN. Empirical results on three sequential modeling tasks further demonstrate that ParaRNN achieves performance comparable to vanilla RNNs while offering improved interpretability and efficiency.

stat.ML↗

arXiv2025

SARMA: Scalable Low-Rank High-Dimensional Autoregressive Moving Averages via Tensor Decomposition

Existing models for high-dimensional time series are overwhelmingly developed within the finite-order vector autoregressive (VAR) framework. However, the more flexible vector autoregressive moving averages (VARMA) have been much less considered. This paper introduces a Tucker-low-rank framework to efficiently capture VARMA-type dynamics for high-dimensional time series, named the Scalable ARMA (SARMA) model. It generalizes the Tucker-low-rank finite-order VAR model to the infinite-order case via flexible parameterizations of the AR coefficient tensor along the temporal dimension. The resulting model enables dynamic factor extraction across response and predictor variables, facilitating interpretation of group patterns. Additionally, we consider sparsity assumptions on the factor loadings to accomplish automatic variable selection and greater estimation efficiency. Both rank-constrained and sparsity-inducing estimators are developed for the proposed model, along with algorithms and model selection methods. The validity of our theory and empirical advantages of our approach are confirmed by simulation studies and real data examples.

stat.ME↗

arXiv2024

Contrastive Learning on Multimodal Analysis of Electronic Health Records

Electronic health record (EHR) systems capture a wealth of multimodal clinical data, encompassing both structured clinical codes and unstructured clinical notes. Yet, many EHR-focused studies have traditionally examined these modalities in isolation or combined them using simplistic methods, overlooking the intrinsic synergy between them. In reality, these modalities are deeply interconnected, each containing clinically relevant and complementary information that, when integrated effectively, can provide a more comprehensive understanding of patient health. Despite the success of multimodal contrastive learning in vision-language applications, its potential remains under-explored in multimodal EHR, particularly in terms of theoretical understanding. To support statistical analysis of multimodal EHR data, we propose a multimodal feature embedding generative model and design a multimodal contrastive loss to learn EHR feature representations. Our theoretical analysis demonstrates the effectiveness of multimodal learning over single-modality learning and connects the solution of the loss function to the singular value decomposition of a pointwise mutual information matrix. This connection leads to a privacy-preserving algorithm tailored for multimodal EHR representation learning. Simulation studies show that the proposed algorithm performs well under a variety of configurations. We further validate its clinical utility using real-world EHR data.

stat.ML↗

arXiv2023

Supervised Factor Modeling for High-Dimensional Linear Time Series

Motivated by Tucker tensor decomposition, this paper imposes low-rank structures to the column and row spaces of coefficient matrices in a multivariate infinite-order vector autoregression (VAR), which leads to a supervised factor model with two factor modelings being conducted to responses and predictors simultaneously. Interestingly, the stationarity condition implies an intrinsic weak group sparsity mechanism of infinite-order VAR, and hence a rank-constrained group Lasso estimation is considered for high-dimensional linear time series. Its non-asymptotic properties are discussed thoughtfully by balancing the estimation, approximation and truncation errors. Moreover, an alternating gradient descent algorithm with thresholding is designed to search for high-dimensional estimates, and its theoretical justifications, including statistical and convergence analysis, are also provided. Theoretical and computational properties of the proposed methodology are verified by simulation experiments, and the advantages over existing methods are demonstrated by two real examples.

stat.ME↗

arXiv2021

A New Measure of Model Redundancy for Compressed Convolutional Neural Networks

While recently many designs have been proposed to improve the model efficiency of convolutional neural networks (CNNs) on a fixed resource budget, theoretical understanding of these designs is still conspicuously lacking. This paper aims to provide a new framework for answering the question: Is there still any remaining model redundancy in a compressed CNN? We begin by developing a general statistical formulation of CNNs and compressed CNNs via the tensor decomposition, such that the weights across layers can be summarized into a single tensor. Then, through a rigorous sample complexity analysis, we reveal an important discrepancy between the derived sample complexity and the naive parameter counting, which serves as a direct indicator of the model redundancy. Motivated by this finding, we introduce a new model redundancy measure for compressed CNNs, called the $K/R$ ratio, which further allows for nonlinear activations. The usefulness of this new measure is supported by ablation studies on popular block designs and datasets.

cs.LG↗

arXiv2020

Do RNN and LSTM have Long Memory?

The LSTM network was proposed to overcome the difficulty in learning long-term dependence, and has made significant advancements in applications. With its success and drawbacks in mind, this paper raises the question - do RNN and LSTM have long memory? We answer it partially by proving that RNN and LSTM do not have long memory from a statistical perspective. A new definition for long memory networks is further introduced, and it requires the model weights to decay at a polynomial rate. To verify our theory, we convert RNN and LSTM into long memory networks by making a minimal modification, and their superiority is illustrated in modeling long-term dependence of various datasets.

stat.ML↗

arXiv2019

Compact Autoregressive Network

Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the huge amount of parameters in the network lead to expensive computational cost and low learning efficiency. The problem can be alleviated slightly by introducing one more narrow hidden layer to the network, but the sample size required to achieve a certain training error is still large. To address this challenge, we rearrange the weight matrices of a linear autoregressive network into a tensor form, and then make use of Tucker decomposition to represent low-rank structures. This leads to a novel compact autoregressive network, called Tucker AutoRegressive (TAR) net. Interestingly, the TAR net can be applied to sequences with long-range dependence since the dimension along the sequential order is reduced. Theoretical studies show that the TAR net improves the learning efficiency, and requires much fewer samples for model training. Experiments on synthetic and real-world datasets demonstrate the promising performance of the proposed compact network.

cs.LG↗