Sublinear-Time Quadratic Minimization via Spectral Decomposition of Matrices

  title={Sublinear-Time Quadratic Minimization via Spectral Decomposition of Matrices},
  author={Amit Levi and Yuichi Yoshida},
We design a sublinear-time approximation algorithm for quadratic function minimization problems with a better error bound than the previous algorithm by Hayashi and Yoshida (NIPS'16). Our approximation algorithm can be modified to handle the case where the minimization is done over a sphere. The analysis of our algorithms is obtained by combining results from graph limit theory, along with a novel spectral decomposition of matrices. Specifically, we prove that a matrix A can be decomposed into… 

Figures and Tables from this paper



Quick Approximation to Matrices and Applications

The matrix approximation is generalized to multi-dimensional arrays and from that derive approximation algorithms for all dense Max-SNP problems and the Regularity Lemma is derived.

Sublinear Optimization for Machine Learning

Lower bounds are given which show the running times of many of the algorithms to be nearly best possible in the unit-cost RAM model and implementations of these algorithms in the semi-streaming setting, obtaining the first low pass polylogarithmic space and sub linear time algorithms achieving arbitrary approximation factor.

The regularity lemma and approximation schemes for dense problems

  • A. FriezeR. Kannan
  • Mathematics
    Proceedings of 37th Conference on Foundations of Computer Science
  • 1996
The central point here is that the Regularity Lemma provides an explanation of why these Max-SNP hard problems turn out to be easy in dense graphs.

Interior Point Methods in Semidefinite Programming with Applications to Combinatorial Optimization

It is argued that many known interior point methods for linear programs can be transformed in a mechanical way to algorithms for SDP with proofs of convergence and polynomial time complexity carrying over in a similar fashion.

Fast Monte-Carlo algorithms for finding low-rank approximations

  • A. FriezeR. KannanS. Vempala
  • Computer Science
    Proceedings 39th Annual Symposium on Foundations of Computer Science (Cat. No.98CB36280)
  • 1998
This paper develops an algorithm which is qualitatively faster provided the entries of the matrix are sampled according to a natural probability distribution and the algorithm takes time polynomial in k, 1//spl epsiv/, log(1//spl delta/) only, independent of m, n.

New Results on Quadratic Minimization

This paper proposes a polynomial-time solution procedure for the extended trust region subproblem arising from solving nonlinear programs with a single equality constraint, and introduces a parameterized problem and proves the existence of a trajectory that will lead to an optimal solution.

Cut-norms and spectra of matrices

One of the aims of this paper is to solve an open problem of Lovasz about relations between graph spectra and cut-distance. The paper starts with several inequalities between two versions of the

A Derivative-Free Algorithm for Least-Squares Minimization

The local quadratic convergence of the DFLS algorithm for zero residual problems is established and numerical experiments indicate that the algorithm is also very promising for achieving high accuracy solutions compared with software packages that do not exploit the special structure of the least-squares problem or that use finite differences to approximate the gradients.

A linear-time algorithm for trust region problems

This work gives the first provable linear-time (in the number of non-zero entries of the input) algorithm for approximately solving the fundamental problem of minimizing a general quadratic function over an ellipsoidal domain.

Hidden convexity in some nonconvex quadratically constrained quadratic programming

It is shown that the original problem is equivalent to a convex minimization problem with simple linear constraints, and a special problem of minimizing a concave quadratic function subject to finitely many convexquadratic constraints, which is also shown to be equivalents to a minimax convex problem.