paper-with-me

Papers

Near-Optimal Stochastic Approximation for Online Principal Component Estimation

2016-03-16 · Chris Junchi Li, Mengdi Wang, Han Liu, Tong Zhang

Principal component analysis (PCA) has been a prominent tool for high-dimensional data analysis. Online algorithms that estimate the principal component by processing streaming data are of tremendous practical and theoretical interests. Despite its rich applications, theoretical convergence analysis remains largely open. In this paper, we cast online PCA into a stochastic nonconvex optimization problem, and we analyze the online PCA algorithm as a stochastic approximation iteration. The stochastic approximation iteration processes data points incrementally and maintains a running estimate of the principal component. We prove for the first time a nearly optimal finite-sample error bound for the online PCA algorithm. Under the subgaussian assumption, we show that the finite-sample error bound closely matches the minimax information lower bound.

📄 PDF Abstract BibTeX arXiv:1603.05305

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Similar Papers 제목 키워드 기반

Stochastic Approximation Algorithms for Principal Component Analysis

2019-01-07 · Jian Vora

Principal Component Analysis is a novel way of of dimensionality reduction. This problem essentially boils down to finding the top k eigen vectors of the data covariance matrix. A considerable amount of literature is fou…

Computational EfficiencyDimensionality ReductionStochastic Optimization

Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding

2023-04-08 · Zhaolin Ren, Tongzheng Ren, Haitong Ma, Na Li 외

This paper proposes an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems. This method reveals an infinite-dimensional feature representation induced by the system's…

Diffusion Approximations for Online Principal Component Estimation and Global Convergence

2018-08-29 · NeurIPS 2017 12 · Chris Junchi Li, Mengdi Wang, Han Liu, Tong Zhang

In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis. Oja's iteration ma…

Fast Nonlinear Two-Time-Scale Stochastic Approximation: Achieving $O(1/k)$ Finite-Sample Complexity

2024-01-23 · Thinh T. Doan

This paper proposes to develop a new variant of the two-time-scale stochastic approximation to find the roots of two coupled nonlinear operators, assuming only noisy samples of these operators can be observed. Our key id…

Causal Inference in Possibly Nonlinear Factor Models

2020-08-31 · Yingjie Feng

This paper develops a general causal inference method for treatment effects models with noisily measured confounders. The key feature is that a large set of noisy measurements are linked with the underlying latent confou…

Causal Inferencecounterfactual