Non-Sparse PCA in High Dimensions via Cone Projected Power Iteration

• URL: http://arxiv.org/abs/2005.07587v2
• Date: Sun, 28 Feb 2021 17:22:55 GMT
• Title: Non-Sparse PCA in High Dimensions via Cone Projected Power Iteration
• Abstract summary: We propose a cone projected power algorithm to recover the first principal eigenvector from a noisy positive semidefinite matrix. Our numerical experiments on simulated and real data, show that our method achieves shorter run time and smaller error in comparison to the ordinary power and some sparse principal component analysis algorithms.
• Score: 4.162663632560141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a cone projected power iteration algorithm to recover the first principal eigenvector from a noisy positive semidefinite matrix. When the true principal eigenvector is assumed to belong to a convex cone, the proposed algorithm is fast and has a tractable error. Specifically, the method achieves polynomial time complexity for certain convex cones equipped with fast projection such as the monotone cone. It attains a small error when the noisy matrix has a small cone-restricted operator norm. We supplement the above results with a minimax lower bound of the error under the spiked covariance model. Our numerical experiments on simulated and real data, show that our method achieves shorter run time and smaller error in comparison to the ordinary power iteration and some sparse principal component analysis algorithms if the principal eigenvector is in a convex cone.

Related papers

• Fast Length-Squared Sampling for Positive-Semidefinite Matrices [15.092552206493544]
  We describe a simple rejection-sampling-based algorithm to perform length-squared sampling on a matrix.<n>The algorithm runs in just $On)$ expected time, which is significantly sublinear in the input size.
  arXiv  Detail & Related papers  (2026-08-12T18:33:22Z)
• Entrywise error bounds for low-rank approximations of kernel matrices [55.524284152242096]
  We derive entrywise error bounds for low-rank approximations of kernel matrices obtained using the truncated eigen-decomposition. A key technical innovation is a delocalisation result for the eigenvectors of the kernel matrix corresponding to small eigenvalues. We validate our theory with an empirical study of a collection of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-05-23T12:26:25Z)
• Fast Optimal Locally Private Mean Estimation via Random Projections [58.603579803010796]
  We study the problem of locally private mean estimation of high-dimensional vectors in the Euclidean ball. We propose a new algorithmic framework, ProjUnit, for private mean estimation. Our framework is deceptively simple: each randomizer projects its input to a random low-dimensional subspace, normalizes the result, and then runs an optimal algorithm.
  arXiv  Detail & Related papers  (2023-06-07T14:07:35Z)
• Efficient distributed representations with linear-time attention scores normalization [3.8673630752805437]
  We propose a linear-time approximation of the attention score normalization constants for embedding vectors with bounded norms. The accuracy of our estimation formula surpasses competing kernel methods by even orders of magnitude. The proposed algorithm is highly interpretable and easily adapted to an arbitrary embedding problem.
  arXiv  Detail & Related papers  (2023-03-30T15:48:26Z)
• Near optimal sample complexity for matrix and tensor normal models via geodesic convexity [5.191641077435773]
  We show nonasymptotic bounds for the error achieved by the maximum likelihood estimator (MLE) in several natural metrics. In the same regimes as our sample complexity bounds, we show that an iterative procedure to compute the MLE known as the flip-flop algorithm converges linearly with high probability.
  arXiv  Detail & Related papers  (2021-10-14T17:47:00Z)
• Provable Low Rank Plus Sparse Matrix Separation Via Nonconvex Regularizers [0.0]
  This paper considers a large problem where we seek to recover a low rank matrix/or sparse vector from some set of measurements. While methods based on convex bias estimators suffer from bias the rank or sparsity to be known as a priori, we use non regularizers. We present a novel analysis of the proximal alternating bias descent algorithm applied to such problems.
  arXiv  Detail & Related papers  (2021-09-26T22:09:42Z)
• Analysis of Truncated Orthogonal Iteration for Sparse Eigenvector Problems [78.95866278697777]
  We propose two variants of the Truncated Orthogonal Iteration to compute multiple leading eigenvectors with sparsity constraints simultaneously. We then apply our algorithms to solve the sparse principle component analysis problem for a wide range of test datasets.
  arXiv  Detail & Related papers  (2021-03-24T23:11:32Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)
• Sparse PCA via $l_{2,p}$-Norm Regularization for Unsupervised Feature Selection [138.97647716793333]
  We propose a simple and efficient unsupervised feature selection method, by combining reconstruction error with $l_2,p$-norm regularization. We present an efficient optimization algorithm to solve the proposed unsupervised model, and analyse the convergence and computational complexity of the algorithm theoretically.
  arXiv  Detail & Related papers  (2020-12-29T04:08:38Z)
• Dynamical perturbation theory for eigenvalue problems [0.0]
  We show that our algorithm outperforms the usual Rayleigh-Schr"odinger expansion on three counts. Our scheme also scales better with the size of the matrix than general-purpose eigenvalue routines.
  arXiv  Detail & Related papers  (2020-02-28T17:13:22Z)
• Optimal Randomized First-Order Methods for Least-Squares Problems [56.05635751529922]
  This class of algorithms encompasses several randomized methods among the fastest solvers for least-squares problems. We focus on two classical embeddings, namely, Gaussian projections and subsampled Hadamard transforms. Our resulting algorithm yields the best complexity known for solving least-squares problems with no condition number dependence.
  arXiv  Detail & Related papers  (2020-02-21T17:45:32Z)

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.