paper-with-me

홈 › Papers

Convergence of Stochastic Gradient Descent for PCA

2015-09-30 · Ohad Shamir

We consider the problem of principal component analysis (PCA) in a streaming stochastic setting, where our goal is to find a direction of approximate maximal variance, based on a stream of i.i.d. data points in $\reals^d$. A simple and computationally cheap algorithm for this is stochastic gradient descent (SGD), which incrementally updates its estimate based on each new data point. However, due to the non-convex nature of the problem, analyzing its performance has been a challenge. In particular, existing guarantees rely on a non-trivial eigengap assumption on the covariance matrix, which is intuitively unnecessary. In this paper, we provide (to the best of our knowledge) the first eigengap-free convergence guarantees for SGD in the context of PCA. This also partially resolves an open problem posed in \cite{hardt2014noisy}. Moreover, under an eigengap assumption, we show that the same techniques lead to new SGD convergence guarantees with better dependence on the eigengap.

📄 PDF Abstract BibTeX arXiv:1509.09002

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…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Weighted Low-rank Approximation via Stochastic Gradient Descent on Manifolds

2025-02-20 · Conglong Xu, Peiqi Yang, Hao Wu

We solve a regularized weighted low-rank approximation problem by a stochastic gradient descent on a manifold. To guarantee the convergence of our stochastic gradient descent, we establish a convergence theorem on manifo…

Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates

2021-10-25 · Theodoros Mamalis, Dusan Stipanovic, Petros Voulgaris

Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradient information to solve these problems.…

The convergence of the Stochastic Gradient Descent (SGD) : a self-contained proof

2021-03-26 · Gabrel Turinici

We give here a proof of the convergence of the Stochastic Gradient Descent (SGD) in a self-contained manner.

Conditional Accelerated Lazy Stochastic Gradient Descent

2017-03-16 · ICML 2017 8 · Guanghui Lan, Sebastian Pokutta, Yi Zhou, Daniel Zink

In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate $O\left(\frac{1}{\varepsilon^2}\right)$ …

Linear Convergence of Generalized Mirror Descent with Time-Dependent Mirrors

2020-09-18 · Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

The Polyak-Lojasiewicz (PL) inequality is a sufficient condition for establishing linear convergence of gradient descent, even in non-convex settings. While several recent works use a PL-based analysis to establish linea…