Block layer decomposition schemes for training deep neural networks

DOI10.1007/s10898-019-00856-0zbMath1441.90127arXiv2003.08123OpenAlexW3105298458WikidataQ126808254 ScholiaQ126808254MaRDI QIDQ2173515

Laura Palagi, Ruggiero Seccia

Publication date: 23 April 2020

Published in: Journal of Global Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.08123

zbMATH Keywords

online optimizationlarge scale optimizationdeep feedforward neural networksblock coordinate decomposition

Mathematics Subject Classification ID

Large-scale problems in mathematical programming (90C06) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

On the convergence of a block-coordinate incremental gradient method

Uses Software

• SciPy
• Keras
• AdaGrad
• RMSprop
• Adam
• Saga

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An incremental decomposition method for unconstrained optimization
• Coordinate descent algorithms
• Efficient block-coordinate descent algorithms for the group Lasso
• Global optimization issues in deep network regression: an overview
• Convergent Decomposition Techniques for Training RBF Neural Networks
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Globally convergent block-coordinate techniques for unconstrained optimization
• Gradient Convergence in Gradient methods with Errors
• Optimization Methods for Large-Scale Machine Learning
• Incremental Least Squares Methods and the Extended Kalman Filter
• On the Convergence of Block Coordinate Descent Type Methods
• A Stochastic Approximation Method