Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization

Abstract

Stochastic optimization naturally arises in machine learning. Efficient algorithms with provable guarantees, however, are still largely missing, when the objective function is nonconvex and the data points are dependent. This paper studies this fundamental challenge through a streaming PCA problem for stationary time series data. Specifically, our goal is to estimate the principle component of time series data with respect to the covariance matrix of the stationary distribution. Computationally, we propose a variant of Oja's algorithm combined with downsampling to control the bias of the stochastic gradient caused by the data dependency. Theoretically, we quantify the uncertainty of our proposed stochastic algorithm based on diffusion approximations. This allows us to prove the asymptotic rate of convergence and further implies near optimal asymptotic sample complexity. Numerical experiments are provided to support our analysis.

References in corpus (6)

• Basic Properties of Strong Mixing Conditions. A Survey and Some Open Questions
• Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes
• Matrix Completion has No Spurious Local Minimum
• Complete Dictionary Recovery over the Sphere
• Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
• First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate

Cited by in corpus (2)

• AdaOja: Adaptive Learning Rates for Streaming PCA
• A Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization