Adaptive and Implicit Regularization for Matrix Completion

DOI10.1137/22M1489228MaRDI QIDQ5056933zbMATH OpenFDO

Authors Zhemin Li, Tao Sun, Hongxia Wang, Bao Wang

Publication date 8 December 2022

Published in SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2208.05640

zbMATH Keywords

deep learningmatrix completionlow-rank regularizationadaptive and implicit regularization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Knowledge representation (68T30) General topics in artificial intelligence (68T01)

Recommendations

• Adaptive Low Rank Matrix Completion
• An adaptation for iterative structured matrix completion
• Adaptive multinomial matrix completion
• Matrix completion via an alternating direction method
• An ADMM-factorization algorithm for low rank matrix completion
• Some empirical advances in matrix completion
• A Riemannian rank-adaptive method for low-rank matrix completion
• Matrix completion via minimizing an approximate rank
• Adaptive confidence sets for matrix completion
• Matrix completion via max-norm constrained optimization

Cites work

• A mean field view of the landscape of two-layer neural networks
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• Exact matrix completion via convex optimization
• Learning the parts of objects by non-negative matrix factorization
• Multifidelity Dimension Reduction via Active Subspaces
• Non-blind and blind deconvolution under Poisson noise using fractional-order total variation
• Nonlinear total variation based noise removal algorithms
• Nonlocal Image Restoration With Bilateral Variance Estimation: A Low-Rank Approach
• Scheduled restart momentum for accelerated stochastic gradient descent
• Some methods of speeding up the convergence of iteration methods
• Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
• Wide neural networks of any depth evolve as linear models under gradient descent ^*

Cited in

(3)

• Manifold regularized matrix completion for multi-label learning with ADMM
• An adaptation for iterative structured matrix completion
• Approximation Newton method for low-rank matrix completion

Describes a project that uses

Uses Software

• Tensor2Tensor
• Adam
• impute

This page was built for publication: Adaptive and Implicit Regularization for Matrix Completion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5056933)