Tuning parameters of deep neural network training algorithms pays off: a computational study

DOI10.1007/s11750-024-00683-xMaRDI QIDQ6635854

Lorenzo Papa, Laura Palagi, Irene Amerini, Marco Boresta, Corrado Coppola

Publication date: 12 November 2024

Published in: Top (Search for Journal in Brave)

zbMATH Keywords

large-scale optimizationmachine learningconvolutional neural networkdeep network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Applications of mathematical programming (90C90)

Cites Work

• Unnamed Item
• Unnamed Item
• Support vector machines maximizing geometric margins for multi-class classification
• Mathematical optimization in classification and regression trees
• On the limited memory BFGS method for large scale optimization
• Machine learning models and algorithms for big data classification. Thinking with examples for effective learning
• A comparative study of the leading machine learning techniques and two new optimization algorithms
• Optimization problems for machine learning: a survey
• High-dimensional dynamics of generalization error in neural networks
• First-order and stochastic optimization methods for machine learning
• Global optimization issues in deep network regression: an overview
• Support Vector Machines
• Numerical Optimization
• Gradient Convergence in Gradient methods with Errors
• Optimization Methods for Large-Scale Machine Learning
• A robust multi-batch L-BFGS method for machine learning
• Data Mining and Knowledge Discovery Handbook
• Benchmarking Derivative-Free Optimization Algorithms
• A Stochastic Approximation Method
• Suboptimal Local Minima Exist for Wide Neural Networks with Smooth Activations
• A jamming transition from under- to over-parametrization affects generalization in deep learning
• Optimal classification trees
• A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms
• Benchmarking optimization software with performance profiles.

Related Items (1)

Guest editorial to the special issue on machine learning and mathematical optimization in top-transactions in operations research

This page was built for publication: Tuning parameters of deep neural network training algorithms pays off: a computational study