cs.LGJun 7, 2023

Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation

Authors: Zhao Song, Mingquan Ye, Junze Yin, Lichen Zhang

Organizations: Simons Institute for the Theory of Computing, UC Berkeley · University of Illinois, Chicago · Rice University · Massachusetts Institute of Technology

Abstract

Weighted low rank approximation is a fundamental problem in numerical linear algebra, and it has many applications in machine learning. Given a matrix M∈Rn×nM \in \mathbb{R}^{n \times n}, a non-negative weight matrix W∈R≥0n×nW \in \mathbb{R}_{\geq 0}^{n \times n}, a parameter kk, the goal is to output two matrices X,Y∈Rn×kX,Y\in \mathbb{R}^{n \times k} such that ∥W∘(M−XY⊤)∥F\| W \circ (M - X Y^\top) \|_F is minimized, where ∘\circ denotes the Hadamard product. It naturally generalizes the well-studied low rank matrix completion problem. Such a problem is known to be NP-hard and even hard to approximate assuming the Exponential Time Hypothesis [GG11, RSW16]. Meanwhile, alternating minimization is a good heuristic solution for weighted low rank approximation. In particular, [LLR16] shows that, under mild assumptions, alternating minimization does provide provable guarantees. In this work, we develop an efficient and robust framework for alternating minimization that allows the alternating updates to be computed approximately. For weighted low rank approximation, this improves the cost of each iteration of [LLR16] from ∥W∥0k2\|W\|_0k^2 to ∥W∥0k\|W\|_0 k where ∥W∥0\|W\|_0 denotes the number of nonzero entries of the weight matrix. At the heart of our framework is a high-accuracy multiple response regression solver together with a robust analysis of alternating minimization. We also replace the random initialization of [LLR16], whose claimed guarantee fails, by subspace iteration from a Gaussian start, so our total running time of O~((∥W∥0k+nk3)log⁡(1/ε))\widetilde O((\|W\|_0 k+nk^3)\log(1/ε)) includes the initialization. In exchange, our guarantee needs the weight matrix to be within spectral distance γnγn of the all-ones matrix for a γγ that is polynomially small in nn.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time

    Feb 21, 2023Yuzhou Gu, Zhao Song, Junze Yin +1alternating minimizationMatrix Completion

  2. Accelerating Power Method with Fast Sketching for Stronger Low-Rank Approximation

    May 10, 2026Shabarish Chenakkod, Michał DerezińskiLow-Rank Matrix DecompositionNyström Method

  3. Unbiased Low-Rank Approximation for Repeated Matrix-Vector Multiplication: Stability and Optimal Sampling

    Oct 31, 2026Kang LiuLow-Rank Approximation