Adaptive and Implicit Regularization for Matrix Completion

DOI10.1137/22M1489228MaRDI QIDQ5056933

Zhemin Li, Bao Wang, Hong-Xia Wang, Tao Sun

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

matrix completiondeep learninglow-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)

Uses Software

• impute
• Adam
• Tensor2Tensor

Cites Work

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

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