DSLGJun 2, 2023

Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization

arXiv:2306.01869v15 citationsh-index: 58
Originality Highly original
AI Analysis

This provides a near-optimal solution for BMF, which is important for applications in data analysis and machine learning where binary data is common, representing a significant theoretical advance over prior work.

The paper tackles the binary matrix factorization (BMF) problem by developing efficient algorithms that achieve a (1+ε)-approximation for minimizing Frobenius loss, improving upon the previous constant-factor approximation of at least 576, with running time singly exponential in the small rank parameter k.

We introduce efficient $(1+\varepsilon)$-approximation algorithms for the binary matrix factorization (BMF) problem, where the inputs are a matrix $\mathbf{A}\in\{0,1\}^{n\times d}$, a rank parameter $k>0$, as well as an accuracy parameter $\varepsilon>0$, and the goal is to approximate $\mathbf{A}$ as a product of low-rank factors $\mathbf{U}\in\{0,1\}^{n\times k}$ and $\mathbf{V}\in\{0,1\}^{k\times d}$. Equivalently, we want to find $\mathbf{U}$ and $\mathbf{V}$ that minimize the Frobenius loss $\|\mathbf{U}\mathbf{V} - \mathbf{A}\|_F^2$. Before this work, the state-of-the-art for this problem was the approximation algorithm of Kumar et. al. [ICML 2019], which achieves a $C$-approximation for some constant $C\ge 576$. We give the first $(1+\varepsilon)$-approximation algorithm using running time singly exponential in $k$, where $k$ is typically a small integer. Our techniques generalize to other common variants of the BMF problem, admitting bicriteria $(1+\varepsilon)$-approximation algorithms for $L_p$ loss functions and the setting where matrix operations are performed in $\mathbb{F}_2$. Our approach can be implemented in standard big data models, such as the streaming or distributed models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes