Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks

• URL: http://arxiv.org/abs/2410.09640v2
• Date: Mon, 21 Oct 2024 08:33:44 GMT
• Title: Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks
• Authors: Zhenghao Xu, Yuqing Wang, Tuo Zhao, Rachel Ward, Molei Tao,
• Abstract summary: We prove that Nesterov's accelerated gradient attains an complexity $O(kappalogfrac1epsilon)$. In particular, we prove that NAG can also attain an accelerated linear convergence rate.
• Score: 46.04785603483612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the convergence rate of first-order methods for rectangular matrix factorization, which is a canonical nonconvex optimization problem. Specifically, given a rank-$r$ matrix $\mathbf{A}\in\mathbb{R}^{m\times n}$, we prove that gradient descent (GD) can find a pair of $\epsilon$-optimal solutions $\mathbf{X}_T\in\mathbb{R}^{m\times d}$ and $\mathbf{Y}_T\in\mathbb{R}^{n\times d}$, where $d\geq r$, satisfying $\lVert\mathbf{X}_T\mathbf{Y}_T^\top-\mathbf{A}\rVert_\mathrm{F}\leq\epsilon\lVert\mathbf{A}\rVert_\mathrm{F}$ in $T=O(\kappa^2\log\frac{1}{\epsilon})$ iterations with high probability, where $\kappa$ denotes the condition number of $\mathbf{A}$. Furthermore, we prove that Nesterov's accelerated gradient (NAG) attains an iteration complexity of $O(\kappa\log\frac{1}{\epsilon})$, which is the best-known bound of first-order methods for rectangular matrix factorization. Different from small balanced random initialization in the existing literature, we adopt an unbalanced initialization, where $\mathbf{X}_0$ is large and $\mathbf{Y}_0$ is $0$. Moreover, our initialization and analysis can be further extended to linear neural networks, where we prove that NAG can also attain an accelerated linear convergence rate. In particular, we only require the width of the network to be greater than or equal to the rank of the output label matrix. In contrast, previous results achieving the same rate require excessive widths that additionally depend on the condition number and the rank of the input data matrix.

Related papers

• In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting [21.002519159190538]
  We analyze a distributed algorithm to compute a low-rank matrix factorization on $N$ clients. We obtain a global $mathbfV$ in $mathbbRd times r$ common to all clients and a local $mathbfUi$ in $mathbbRn_itimes r$.
  arXiv  Detail & Related papers  (2024-09-13T12:28:42Z)
• Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms [50.15964512954274]
  We study the problem of residual error estimation for matrix and vector norms using a linear sketch. We demonstrate that this gives a substantial advantage empirically, for roughly the same sketch size and accuracy as in previous work. We also show an $Omega(k2/pn1-2/p)$ lower bound for the sparse recovery problem, which is tight up to a $mathrmpoly(log n)$ factor.
  arXiv  Detail & Related papers  (2024-08-16T02:33:07Z)
• Provably learning a multi-head attention layer [55.2904547651831]
  Multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models. In this work, we initiate the study of provably learning a multi-head attention layer from random examples. We prove computational lower bounds showing that in the worst case, exponential dependence on $m$ is unavoidable.
  arXiv  Detail & Related papers  (2024-02-06T15:39:09Z)
• Optimal Estimator for Linear Regression with Shuffled Labels [17.99906229036223]
  This paper considers the task of linear regression with shuffled labels. $mathbf Y in mathbb Rntimes m, mathbf Pi in mathbb Rntimes p, mathbf B in mathbb Rptimes m$, and $mathbf Win mathbb Rntimes m$, respectively.
  arXiv  Detail & Related papers  (2023-10-02T16:44:47Z)
• Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization [54.29685789885059]
  We introduce efficient $(1+varepsilon)$-approximation algorithms for the binary matrix factorization (BMF) problem. The goal is to approximate $mathbfA$ as a product of low-rank factors. Our techniques generalize to other common variants of the BMF problem.
  arXiv  Detail & Related papers  (2023-06-02T18:55:27Z)
• Convergence of Alternating Gradient Descent for Matrix Factorization [5.439020425819001]
  We consider alternating gradient descent (AGD) with fixed step size applied to the asymmetric matrix factorization objective. We show that, for a rank-$r$ matrix $mathbfA in mathbbRm times n$, smoothness $C$ in the complexity $T$ to be an absolute constant.
  arXiv  Detail & Related papers  (2023-05-11T16:07:47Z)
• Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
  We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
  arXiv  Detail & Related papers  (2022-06-17T17:55:43Z)
• Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization [49.090785356633695]
  We study the asymmetric low-rank factorization problem: [mathbfU in mathbbRm min d, mathbfU$ and mathV$.
  arXiv  Detail & Related papers  (2021-06-27T17:25:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.