Combinatorial Sparse PCA Beyond the Spiked Identity Model

• URL: http://arxiv.org/abs/2603.02607v1
• Date: Tue, 03 Mar 2026 05:19:55 GMT
• Title: Combinatorial Sparse PCA Beyond the Spiked Identity Model
• Authors: Syamantak Kumar, Purnamrita Sarkar, Kevin Tian, Peiyuan Zhang,
• Abstract summary: We present a method for sparse PCA that provably succeeds for general $$ using $s2 cdot mathrmpolylog(d)$ samples and $d2 cdot mathrmpoly(s)$ time.<n>We also evaluate our method on synthetic and real-world datasets.
• Score: 25.073817053937802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse PCA is one of the most well-studied problems in high-dimensional statistics. In this problem, we are given samples from a distribution with covariance $Σ$, whose top eigenvector $v \in R^d$ is $s$-sparse. Existing sparse PCA algorithms can be broadly categorized into (1) combinatorial algorithms (e.g., diagonal or elementwise covariance thresholding) and (2) SDP-based algorithms. While combinatorial algorithms are much simpler, they are typically only analyzed under the spiked identity model (where $Σ= I_d + γvv^\top$ for some $γ> 0$), whereas SDP-based algorithms require no additional assumptions on $Σ$. We demonstrate explicit counterexample covariances $Σ$ against the success of standard combinatorial algorithms for sparse PCA, when moving beyond the spiked identity model. In light of this discrepancy, we give the first combinatorial method for sparse PCA that provably succeeds for general $Σ$ using $s^2 \cdot \mathrm{polylog}(d)$ samples and $d^2 \cdot \mathrm{poly}(s, \log(d))$ time, by providing a global convergence guarantee on a variant of the truncated power method of Yuan and Zhang (2013). We provide a natural generalization of our method to recovering a vector in a sparse leading eigenspace. Finally, we evaluate our method on synthetic and real-world sparse PCA datasets.

Related papers

• An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise [8.555773470114698]
  We propose an algorithm capable of estimating the top $k$ eigenvectors for arbitrary $k leq d$.<n>Our algorithm achieves near-optimal statistical error even when $n = tilde!O(d)$.
  arXiv  Detail & Related papers  (2025-08-14T17:48:45Z)
• SoS Certificates for Sparse Singular Values and Their Applications: Robust Statistics, Subspace Distortion, and More [37.208622097149714]
  We give a new family of upper-time algorithms which can certify bounds on the maximum of $|M u|$.<n>Our certification algorithm makes essential use of the Sum-of-Squares hierarchy.
  arXiv  Detail & Related papers  (2024-12-30T18:59:46Z)
• Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs [56.237917407785545]
  We consider the problem of learning an $varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.
  arXiv  Detail & Related papers  (2024-05-10T09:58:47Z)
• Oja's Algorithm for Streaming Sparse PCA [7.059472280274011]
  Oja's algorithm for Streaming Principal Component Analysis (PCA) for $n$ data-points in a $d$ dimensional space achieves the same sin-squared error $O(r_mathsfeff/n)$ as the offline algorithm in $O(d)$ space and $O(nd)$ time.<n>We show that a simple single-pass procedure that thresholds the output of Oja's algorithm can achieve the minimax error bound under some regularity conditions in $O(d)$ space and $O(nd)$ time.
  arXiv  Detail & Related papers  (2024-02-11T16:36:48Z)
• Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials [50.90125395570797]
  We study the problem of PAC learning a linear combination of $k$ ReLU activations under the standard Gaussian distribution on $mathbbRd$ with respect to the square loss. Our main result is an efficient algorithm for this learning task with sample and computational complexity $(dk/epsilon)O(k)$, whereepsilon>0$ is the target accuracy.
  arXiv  Detail & Related papers  (2023-07-24T14:37:22Z)
• Replicable Clustering [57.19013971737493]
  We propose algorithms for the statistical $k$-medians, statistical $k$-means, and statistical $k$-centers problems by utilizing approximation routines for their counterparts in a black-box manner. We also provide experiments on synthetic distributions in 2D using the $k$-means++ implementation from sklearn as a black-box that validate our theoretical results.
  arXiv  Detail & Related papers  (2023-02-20T23:29:43Z)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Robust Sparse Mean Estimation via Sum of Squares [42.526664955704746]
  We study the problem of high-dimensional sparse mean estimation in the presence of an $epsilon$-fraction of adversarial outliers. Our algorithms follow the Sum-of-Squares based, to algorithms approach.
  arXiv  Detail & Related papers  (2022-06-07T16:49:54Z)
• Clustering Mixture Models in Almost-Linear Time via List-Decodable Mean Estimation [58.24280149662003]
  We study the problem of list-decodable mean estimation, where an adversary can corrupt a majority of the dataset. We develop new algorithms for list-decodable mean estimation, achieving nearly-optimal statistical guarantees.
  arXiv  Detail & Related papers  (2021-06-16T03:34:14Z)
• List-Decodable Mean Estimation in Nearly-PCA Time [50.79691056481693]
  We study the fundamental task of list-decodable mean estimation in high dimensions. Our algorithm runs in time $widetildeO(ndk)$ for all $k = O(sqrtd) cup Omega(d)$, where $n$ is the size of the dataset. A variant of our algorithm has runtime $widetildeO(ndk)$ for all $k$, at the expense of an $O(sqrtlog k)$ factor in the recovery guarantee
  arXiv  Detail & Related papers  (2020-11-19T17:21:37Z)

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.