Online Tensor Inference

Abstract

Contemporary applications, such as recommendation systems and mobile health monitoring, require real-time processing and analysis of sequentially arriving high-dimensional tensor data. Traditional offline learning, involving the storage and utilization of all data in each computational iteration, becomes impractical for these tasks. Furthermore, existing low-rank tensor methods lack the capability for online statistical inference, which is essential for real-time predictions and informed decision-making. This paper addresses these challenges by introducing a novel online inference framework for low-rank tensors. Our approach employs Stochastic Gradient Descent (SGD) to enable efficient real-time data processing without extensive memory requirements. We establish a non-asymptotic convergence result for the online low-rank SGD estimator, nearly matches the minimax optimal estimation error rate of offline models. Furthermore, we propose a simple yet powerful online debiasing approach for sequential statistical inference. The entire online procedure, covering both estimation and inference, eliminates the need for data splitting or storing historical data, making it suitable for on-the-fly hypothesis testing. In our analysis, we control the sum of constructed super-martingales to ensure estimates along the entire solution path remain within the benign region. Additionally, a novel spectral representation tool is employed to address statistical dependencies among iterative estimates, establishing the desired asymptotic normality.

Accepted by Operations Research

References in corpus (19)

• Maps of random walks on complex networks reveal community structure
• Incoherence-Optimal Matrix Completion
• Sparse Online Learning via Truncated Gradient
• Low-rank Solutions of Linear Matrix Equations via Procrustes Flow
• Inference and Uncertainty Quantification for Noisy Matrix Completion
• Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent
• Statistical Inference for High-Dimensional Matrix-Variate Factor Model
• Uncertainty Quantification for Matrix Compressed Sensing and Quantum Tomography Problems
• Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients
• Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements
• Power Iteration for Tensor PCA
• Partially Observed Dynamic Tensor Response Regression
• Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent
• Community Detection on Mixture Multi-layer Networks via Regularized Tensor Decomposition
• Heteroskedastic Tensor Clustering
• Online Statistical Inference in Decision-Making with Matrix Context
• Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal Regret
• Estimating Higher-Order Mixed Memberships via the ${\ell }_{2,\infty }$ Tensor Perturbation Bound
• Computationally Efficient and Statistically Optimal Robust Low-rank Matrix and Tensor Estimation