Data-driven algorithm selection and tuning in optimization and signal processing

DOI10.1007/s10472-020-09717-zzbMath1472.65074arXiv1905.13404OpenAlexW3098261982MaRDI QIDQ2043447

Jamie Haddock, Deanna Needell, Anna Ma, Jesús A. De Loera

Publication date: 2 August 2021

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1905.13404

zbMATH Keywords

neural networkscompressed sensingalgorithm selectionhyperparameter tuningautomated machine learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• Regularization tools
• CoSaMP
• MNIST
• ImageNet
• AdaGrad
• Adam
• auto-sklearn
• OBOE
• AlexNet
• ADADELTA
• PRMLT
• Hyperband

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
• A mathematical introduction to compressive sensing
• CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
• Regularization tools: A Matlab package for analysis and solution of discrete ill-posed problems
• Learning a classification of mixed-integer quadratic programming problems
• Learning when to use a decomposition
• Machine learning for combinatorial optimization: a methodological tour d'horizon
• Exact matrix completion via convex optimization
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Performance comparisons of greedy algorithms in compressed sensing
• Hard Thresholding Pursuit: An Algorithm for Compressive Sensing
• On sparse reconstruction from Fourier and Gaussian measurements
• Decoding by Linear Programming
• Neural Networks for Combinatorial Optimization: A Review of More Than a Decade of Research
• Probabilistic Line Searches for Stochastic Optimization
• A PAC Approach to Application-Specific Algorithm Selection
• Signal Space CoSaMP for Sparse Recovery With Redundant Dictionaries
• A Machine Learning-Based Approximation of Strong Branching
• A Stochastic Approximation Method
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm