Low-complexity subspace-descent over symmetric positive definite manifold

• URL: http://arxiv.org/abs/2305.02041v4
• Date: Mon, 18 Dec 2023 11:57:13 GMT
• Title: Low-complexity subspace-descent over symmetric positive definite manifold
• Authors: Yogesh Darmwal, Ketan Rajawat
• Abstract summary: We develop low-complexity algorithms for the minimization of functions over the symmetric positive definite (SPD) manifold. The proposed approach utilizes carefully chosen subspaces that allow the update to be written as a product of the Cholesky factor of the iterate and a sparse matrix.
• Score: 9.346050098365648
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work puts forth low-complexity Riemannian subspace descent algorithms for the minimization of functions over the symmetric positive definite (SPD) manifold. Different from the existing Riemannian gradient descent variants, the proposed approach utilizes carefully chosen subspaces that allow the update to be written as a product of the Cholesky factor of the iterate and a sparse matrix. The resulting updates avoid the costly matrix operations like matrix exponentiation and dense matrix multiplication, which are generally required in almost all other Riemannian optimization algorithms on SPD manifold. We further identify a broad class of functions, arising in diverse applications, such as kernel matrix learning, covariance estimation of Gaussian distributions, maximum likelihood parameter estimation of elliptically contoured distributions, and parameter estimation in Gaussian mixture model problems, over which the Riemannian gradients can be calculated efficiently. The proposed uni-directional and multi-directional Riemannian subspace descent variants incur per-iteration complexities of $O(n)$ and $O(n^2)$ respectively, as compared to the $O(n^3)$ or higher complexity incurred by all existing Riemannian gradient descent variants. The superior runtime and low per-iteration complexity of the proposed algorithms is also demonstrated via numerical tests on large-scale covariance estimation and matrix square root problems. MATLAB code implementation is publicly available on GitHub : https://github.com/yogeshd-iitk/subspace_descent_over_SPD_manifold

Related papers

• Riemannian Optimization for Non-convex Euclidean Distance Geometry with Global Recovery Guarantees [6.422262171968397]
  Two algorithms are proposed to solve the Euclidean Distance Geometry problem. First algorithm converges linearly to the true solution. Second algorithm demonstrates strong numerical performance on both synthetic and real data.
  arXiv  Detail & Related papers  (2024-10-08T21:19:22Z)
• Obtaining Lower Query Complexities through Lightweight Zeroth-Order Proximal Gradient Algorithms [65.42376001308064]
  We propose two variance reduced ZO estimators for complex gradient problems. We improve the state-of-the-art function complexities from $mathcalOleft(minfracdn1/2epsilon2, fracdepsilon3right)$ to $tildecalOleft(fracdepsilon2right)$.
  arXiv  Detail & Related papers  (2024-10-03T15:04:01Z)
• Riemannian coordinate descent algorithms on matrix manifolds [12.05722932030768]
  We provide a general framework for developing computationally efficient coordinate descent (CD) algorithms on matrix manifold. We propose CD algorithms for various manifold such as Stiefel, Grassmann, (generalized) hyperbolic, symplectic, and symmetric positive (semi)definite. We analyze their convergence and complexity, and empirically illustrate their efficacy in several applications.
  arXiv  Detail & Related papers  (2024-06-04T11:37:11Z)
• Stochastic Optimization for Non-convex Problem with Inexact Hessian Matrix, Gradient, and Function [99.31457740916815]
  Trust-region (TR) and adaptive regularization using cubics have proven to have some very appealing theoretical properties. We show that TR and ARC methods can simultaneously provide inexact computations of the Hessian, gradient, and function values.
  arXiv  Detail & Related papers  (2023-10-18T10:29:58Z)
• Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [49.58290066287418]
  We propose a novel method named Multi-block-probe Variance Reduced (MSVR) to alleviate the complexity of compositional problems. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on strongity.
  arXiv  Detail & Related papers  (2022-07-18T12:03:26Z)
• Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning [54.01682318834995]
  Preconditioning is a highly effective step for any iterative method involving matrix-vector multiplication. We prove that preconditioning has an additional benefit that has been previously unexplored. It simultaneously can reduce variance at essentially negligible cost.
  arXiv  Detail & Related papers  (2021-07-01T06:43:11Z)
• Automatic differentiation for Riemannian optimization on low-rank matrix and tensor-train manifolds [71.94111815357064]
  In scientific computing and machine learning applications, matrices and more general multidimensional arrays (tensors) can often be approximated with the help of low-rank decompositions. One of the popular tools for finding the low-rank approximations is to use the Riemannian optimization.
  arXiv  Detail & Related papers  (2021-03-27T19:56:00Z)
• Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold [7.257751371276488]
  R-ProxSGD and R-ProxSPB are generalizations of proximal SGD and proximal SpiderBoost. R-ProxSPB algorithm finds an $epsilon$-stationary point with $O(epsilon-3)$ IFOs in the online case, and $O(n+sqrtnepsilon-3)$ IFOs in the finite-sum case.
  arXiv  Detail & Related papers  (2020-05-03T23:41:35Z)
• Optimal Iterative Sketching with the Subsampled Randomized Hadamard Transform [64.90148466525754]
  We study the performance of iterative sketching for least-squares problems. We show that the convergence rate for Haar and randomized Hadamard matrices are identical, andally improve upon random projections. These techniques may be applied to other algorithms that employ randomized dimension reduction.
  arXiv  Detail & Related papers  (2020-02-03T16:17:50Z)

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.