A Tight Analysis of Khatri-Rao Oblivious Subspace Embeddings
Data Structures and Algorithms
Summary
The authors study a special kind of random matrix called the Khatri-Rao sketching matrix, which is useful for compressing large, tensor-structured data in computations. Previous work showed that these matrices need more rows than standard random matrices to maintain accuracy when embedding subspaces. The authors improve the theory by proving that the Khatri-Rao matrices can achieve nearly the same efficiency as standard random matrices for any fixed order, improving the required size of the compressed matrix. Their approach relies on two basic properties about the independence and distribution of the columns of these matrices.
Authors
Lorenzo Beretta, Cameron Musco
Abstract
We study random sketching matrices with Khatri-Rao structure. In particular, we consider the Khatri-Rao product (i.e., column-wise tensor product) $A_1\odot\cdots\odot A_d \in \mathbb R^{(n_1 \cdots n_d) \times m}$ of random matrices $A_i \in \mathbb R^{n_i \times m}$ whose columns are isotropic, independent and sub-Gaussian (e.g., Gaussian matrices). Khatri-Rao sketching matrices are widely applied in randomized algorithms for linear algebraic computation and data analysis, when the input data has tensor structure that allows for fast multiplication with $A_1\odot\cdots\odot A_d$. However, existing theory is not able to fully explain their performance in practice. In particular, despite significant attention, our best bounds for the important \emph{oblivious subspace embedding} property with Khatri-Rao matrices lag behind what is achievable with standard unstructured matrices. For embedding a $k$-dimensional subspace to $(1\pm ε)$ error, Bujanović et al. \cite{bujanovic2025subspace} prove that sketching dimension $m = O(k^{3/2}/ε^2)$ suffices in the special case of $d = 2$. Their dependence on $k$ is weaker than the tight bound of $O(k/ε^2)$ known for unstructured sub-Gaussian sketching matrices. In this work, we close this gap, showing that $m = \tilde O(k/ε^2)$ suffices for subspace embedding with a Khatri-Rao sketching matrix with any fixed order $d$. Our proof is simple, leveraging just two basic properties of the Khatri-Rao sketching distribution: 1) the columns of $A_1\odot\cdots\odot A_d \in \mathbb R^{(n_1 \cdots n_d) \times m}$ are independent and isotropic, and 2) each column of $A_1\odot\cdots\odot A_d \in \mathbb R^{(n_1 \cdots n_d) \times m}$ satisfies a weak Johnson-Lindenstrauss type moment property.