Harmless overfitting: using denoising autoencoders in estimation of distribution algorithms

MaRDI QIDQ4969139zbMATH OpenFDO

Authors Malte Probst, Franz Rothlauf

Publication date 5 October 2020

Full work available at URL https://jmlr.csail.mit.edu/papers/v21/16-543.html

zbMATH Keywords

combinatorial optimizationdenoising autoencoderestimation of distribution algorithmneural networksoverfitting

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Combinatorial optimization (90C27) Approximation methods and heuristics in mathematical programming (90C59)

Recommendations

• Learning Structure Illuminates Black Boxes – An Introduction to Estimation of Distribution Algorithms
• A Survey on Estimation of Distribution Algorithms
• MARLEDA: effective distribution estimation through Markov random fields
• Advances in estimation of distribution algorithms
• Comprehensive characterization of the behaviors of estimation of distribution algorithms

Cites work

• Combining variable neighborhood search and estimation of distribution algorithms in the protein side chain placement problem
• Design of modern heuristics. Principles and application.
• Estimating the dimension of a model
• Hierarchical Bayesian optimization algorithm. Toward a new generation of evolutionary algorithms. With a foreword by David E. Goldberg
• scientific article; zbMATH DE number 1702339 (Why is no real title available?)
• scientific article; zbMATH DE number 98525 (Why is no real title available?)
• scientific article; zbMATH DE number 194544 (Why is no real title available?)
• scientific article; zbMATH DE number 2086434 (Why is no real title available?)
• Information-geometric optimization algorithms: a unifying picture via invariance principles
• Learning deep architectures for AI
• Linkage learning via probabilistic modeling in the extended compact genetic algorithm (ECGA)
• Machine learning. A probabilistic perspective
• On over-fitting in model selection and subsequent selection bias in performance evaluation
• Pattern recognition and machine learning.
• Reducing the Dimensionality of Data with Neural Networks
• Scalability of using restricted Boltzmann machines for combinatorial optimization
• The parallel Bayesian optimization algorithm
• Towards a new evolutionary computation. Advances on estimation of distribution algorithms.

Cited in

(1)

• Benign Overfitting and Noisy Features

This page was built for publication: Harmless overfitting: using denoising autoencoders in estimation of distribution algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969139)