Corpus ID: 13168021

Deep Learning for Explicitly Modeling Optimization Landscapes

@article{Baluja2017DeepLF,
  title={Deep Learning for Explicitly Modeling Optimization Landscapes},
  author={S. Baluja},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.07394}
}
  • S. Baluja
  • Published 2017
  • Computer Science
  • ArXiv
  • In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly modeling the interactions between sets of parameters and the overall quality of the solutions discovered. We demonstrate a novel method, based on learning deep networks, to model the global landscapes of optimization problems. To represent the search space… CONTINUE READING
    5 Citations
    Learning deep models of optimization landscapes
    • S. Baluja
    • Computer Science
    • 2017 IEEE Symposium Series on Computational Intelligence (SSCI)
    • 2017
    • PDF
    Envisioning the Benefits of Back-Drive in Evolutionary Algorithms
    • PDF
    Gray-box optimization and factorized distribution algorithms: where two worlds collide
    • 4
    • Highly Influenced
    • PDF
    Evolved GANs for generating pareto set approximations
    • 17

    References

    SHOWING 1-10 OF 50 REFERENCES
    MIMIC: Finding Optima by Estimating Probability Densities
    • 538
    • Highly Influential
    • PDF
    Learning Evaluation Functions to Improve Optimization by Local Search
    • 171
    • Highly Influential
    • PDF
    Topics in black-box combinatorial optimization
    • 23
    Fast Probabilistic Modeling for Combinatorial Optimization
    • 108
    • PDF
    Adam: A Method for Stochastic Optimization
    • 58,485
    • Highly Influential
    • PDF
    Techniques for Learning Binary Stochastic Feedforward Neural Networks
    • 101
    • PDF
    Genetic Algorithms Are NOT Function Optimizers
    • 179
    • PDF
    Tabu Search - Part I
    • 3,670
    • PDF
    Stochastic Hillclimbing as a Baseline Mathod for Evaluating Genetic Algorithms
    • 81
    • PDF