paper-with-me

Papers

Implicit Gradient Neural Networks with a Positive-Definite Mass Matrix for Online Linear Equations Solving

2017-03-17 · Ke Chen

Motivated by the advantages achieved by implicit analogue net for solving online linear equations, a novel implicit neural model is designed based on conventional explicit gradient neural networks in this letter by introducing a positive-definite mass matrix. In addition to taking the advantages of the implicit neural dynamics, the proposed implicit gradient neural networks can still achieve globally exponential convergence to the unique theoretical solution of linear equations and also global stability even under no-solution and multi-solution situations. Simulative results verify theoretical convergence analysis on the proposed neural dynamics.

📄 PDF Abstract BibTeX arXiv:1703.05955

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Spectral-factorized Positive-definite Curvature Learning for NN Training

2025-02-10 · Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae 외

Many training methods, such as Adam(W) and Shampoo, learn a positive-definite curvature matrix and apply an inverse root before preconditioning. Recently, non-diagonal training methods, such as Shampoo, have gained signi…

Riemannian optimization

Implicit regularization and solution uniqueness in over-parameterized matrix sensing

2018-06-06 · Kelly Geyer, Anastasios Kyrillidis, Amir Kalev

We consider whether algorithmic choices in over-parameterized linear matrix factorization introduce implicit regularization. We focus on noiseless matrix sensing over rank-$r$ positive semi-definite (PSD) matrices in $\m…

Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent

2016-05-23 · Qinqing Zheng, John Lafferty

We address the rectangular matrix completion problem by lifting the unknown matrix to a positive semidefinite matrix in higher dimension, and optimizing a nonconvex objective over the semidefinite factor using a simple g…

Matrix Completion

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems

2016-06-04 · Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis 외

We study the projected gradient descent method on low-rank matrix problems with a strongly convex objective. We use the Burer-Monteiro factorization approach to implicitly enforce low-rankness; such factorization introdu…

LEMMAQuantum State TomographyRetrieval

Gradient flow on extensive-rank positive semi-definite matrix denoising

2023-03-16 · Antoine Bodin, Nicolas Macris

In this work, we present a new approach to analyze the gradient flow for a positive semi-definite matrix denoising problem in an extensive-rank and high-dimensional regime. We use recent linear pencil techniques of rando…

Denoising