Shapley values have emerged as a critical tool for explaining which features impact the decisions made by machine learning models. However, computing exact Shapley values is difficult, generally requiring an exponential (in the feature dimension) number of model evaluations. To address this, many model-agnostic randomized estimators have been developed, the most influential and widely used being the KernelSHAP method (Lundberg & Lee, 2017). While related estimators such as unbiased KernelSHAP (Covert & Lee, 2021) and LeverageSHAP (Musco & Witter, 2025) are known to satisfy theoretical guarantees, bounds for KernelSHAP have remained elusive. We describe a broad and unified framework that encompasses KernelSHAP and related estimators constructed using both with and without replacement sampling strategies. We then prove strong non-asymptotic theoretical guarantees that apply to all estimators from our framework. This provides, to the best of our knowledge, the first theoretical guarantees for KernelSHAP and sheds further light on tradeoffs between existing estimators. Through comprehensive benchmarking on small and medium dimensional datasets for Decision-Tree models, we validate our approach against exact Shapley values, consistently achieving low mean squared error with modest sample sizes. Furthermore, we make specific implementation improvements to enable scalability of our methods to high-dimensional datasets. Our methods, tested on datasets such MNIST and CIFAR10, provide consistently better results compared to the KernelSHAP library.

We study algorithms for approximating the spectral density (i.e., the eigenvalue distribution) of a symmetric matrix A ∈ ℝn×n that is accessed through matrix-vector product queries. Recent work has analyzed popular Krylov subspace methods for this problem, showing that they output an ∈ · || A||2 error approximation to the spectral density in the Wasserstein-1 metric using O (1/∈ ) matrix-vector products. By combining a previously studied Chebyshev polynomial moment matching method with a deflation step that approximately projects off the largest magnitude eigendirections of A before estimating the spectral density, we give an improved error bound of ∈ · σℓ (A) using O (ℓ log n + 1/∈ ) matrix-vector products, where σℓ (A) is the ℓth largest singular value of A. In the common case when A exhibits fast singular value decay and so σℓ (A) « ||A||2, our bound can be much stronger than prior work. We also show that it is nearly tight: any algorithm giving error ∈ · σℓ (A) must use Ω(ℓ + 1/∈ ) matrix-vector products.

Let $\mathbf S \in \mathbb R^{n \times n}$ satisfy $\|\mathbf 1-\mathbf S\|_2\leεn$, where $\mathbf 1$ is the all ones matrix and $\|\cdot\|_2$ is the spectral norm. It is well-known that there exists such an $\mathbf S$ with just $O(n/ε^2)$ non-zero entries: we can let $\mathbf S$ be the scaled adjacency matrix of a Ramanujan expander graph. We show that such an $\mathbf S$ yields a $universal$ $sparsifier$ for any positive semidefinite (PSD) matrix. In particular, for any PSD $\mathbf A \in \mathbb{R}^{n\times n}$ with entries bounded in magnitude by $1$, $\|\mathbf A - \mathbf A\circ\mathbf S\|_2 \le εn$, where $\circ$ denotes the entrywise (Hadamard) product. Our techniques also give universal sparsifiers for non-PSD matrices. In this case, letting $\mathbf S$ be the scaled adjacency matrix of a Ramanujan graph with $\tilde O(n/ε^4)$ edges, we have $\|\mathbf A - \mathbf A \circ \mathbf S \|_2 \le ε\cdot \max(n,\|\mathbf A\|_1)$, where $\|\mathbf A\|_1$ is the nuclear norm. We show that the above bounds for both PSD and non-PSD matrices are tight up to log factors. Since $\mathbf A \circ \mathbf S$ can be constructed deterministically, our result for PSD matrices derandomizes and improves upon known results for randomized matrix sparsification, which require randomly sampling ${O}(\frac{n \log n}{ε^2})$ entries. We also leverage our results to give the first deterministic algorithms for several problems related to singular value approximation that run in faster than matrix multiplication time. Finally, if $\mathbf A \in \{-1,0,1\}^{n \times n}$ is PSD, we show that $\mathbf{\tilde A}$ with $\|\mathbf A - \mathbf{\tilde A}\|_2 \le εn$ can be obtained by deterministically reading $\tilde O(n/ε)$ entries of $\mathbf A$. This improves the $1/ε$ dependence on our result for general PSD matrices and is near-optimal.

We study the problem of approximating the eigenspectrum of a symmetric matrix A ∈ ℝ^{n×n} with bounded entries (i.e., ‖A‖_∞ ≤ 1). We present a simple sublinear time algorithm that approximates all eigenvalues of A up to additive error ±εn using those of a randomly sampled Õ((log³ n)/ε³)×Õ((log³ n)/ε³) principal submatrix. Our result can be viewed as a concentration bound on the complete eigenspectrum of a random submatrix, significantly extending known bounds on just the singular values (the magnitudes of the eigenvalues). We give improved error bounds of ± ε √{nnz(A)} and ±ε‖A‖_F when the rows of A can be sampled with probabilities proportional to their sparsities or their squared 𝓁₂ norms respectively. Here nnz(A) is the number of non-zero entries in A and ‖A‖_F is its Frobenius norm. Even for the strictly easier problems of approximating the singular values or testing the existence of large negative eigenvalues (Bakshi, Chepurko, and Jayaram, FOCS '20), our results are the first that take advantage of non-uniform sampling to give improved error bounds. From a technical perspective, our results require several new eigenvalue concentration and perturbation bounds for matrices with bounded entries. Our non-uniform sampling bounds require a new algorithmic approach, which judiciously zeroes out entries of a randomly sampled submatrix to reduce variance, before computing the eigenvalues of that submatrix as estimates for those of A. We complement our theoretical results with numerical simulations, which demonstrate the effectiveness of our algorithms in practice.

We study algorithms for approximating pairwise similarity matrices that arise in natural language processing. Generally, computing a similarity matrix for n data points requires Omega(n^2) similarity computations. This quadratic scaling is a significant bottleneck, especially when similarities are computed via expensive functions, e.g., via transformer models. Approximation methods reduce this quadratic complexity, often by using a small subset of exactly computed similarities to approximate the remainder of the complete pairwise similarity matrix. Significant work focuses on the efficient approximation of positive semidefinite (PSD) similarity matrices, which arise e.g., in kernel methods. However, much less is understood about indefinite (non-PSD) similarity matrices, which often arise in NLP. Motivated by the observation that many of these matrices are still somewhat close to PSD, we introduce a generalization of the popular Nystrom method to the indefinite setting. Our algorithm can be applied to any similarity matrix and runs in sublinear time in the size of the matrix, producing a rank-s approximation with just O(ns) similarity computations. We show that our method, along with a simple variant of CUR decomposition, performs very well in approximating a variety of similarity matrices arising in NLP tasks. We demonstrate high accuracy of the approximated similarity matrices in tasks of document classification, sentence similarity, and cross-document coreference.