Corpus ID: 319311

Efficient Transfer Learning Method for Automatic Hyperparameter Tuning

@inproceedings{Yogatama2014EfficientTL,
  title={Efficient Transfer Learning Method for Automatic Hyperparameter Tuning},
  author={Dani Yogatama and G. Mann},
  booktitle={AISTATS},
  year={2014}
}
  • Dani Yogatama, G. Mann
  • Published in AISTATS 2014
  • Computer Science
  • We propose a fast and effective algorithm for automatic hyperparameter tuning that can generalize across datasets. [...] Key Method The time complexity of reconstructing the response surface at every SMBO iteration in our method is linear in the number of trials (significantly less than previous work with comparable performance), allowing the method to realistically scale to many more datasets. Specifically, we use deviations from the per-dataset mean as the response values. We empirically show the superiority…Expand Abstract
    Transferable Neural Processes for Hyperparameter Optimization
    • 1
    • PDF
    Two-Stage Transfer Surrogate Model for Automatic Hyperparameter Optimization
    • 17
    • Highly Influenced
    • PDF
    Learning to Transfer Initializations for Bayesian Hyperparameter Optimization
    • 1
    • PDF
    Beyond Manual Tuning of Hyperparameters
    • 58
    • Highly Influenced
    A simple transfer-learning extension of Hyperband
    • 4
    • PDF
    A quantile-based approach for hyperparameter transfer learning
    Sequential Model-Free Hyperparameter Tuning
    • 18
    • Highly Influenced
    • PDF
    Using Meta-Learning to Initialize Bayesian Optimization of Hyperparameters
    • 40
    • PDF
    Scalable Gaussian process-based transfer surrogates for hyperparameter optimization
    • 31
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES
    Collaborative hyperparameter tuning
    • 185
    • Highly Influential
    • PDF
    Multi-Task Bayesian Optimization
    • 356
    • PDF
    Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms
    • 753
    • PDF
    Algorithms for Hyper-Parameter Optimization
    • 1,474
    • PDF
    Practical Bayesian Optimization of Machine Learning Algorithms
    • 3,280
    • PDF
    Regularization and variable selection via the elastic net
    • 10,748
    • PDF
    Cutting-plane training of structural SVMs
    • 1,061
    • PDF
    Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
    • 1,024
    • PDF
    Portfolio Allocation for Bayesian Optimization
    • 141
    • PDF
    Gaussian Processes for Machine Learning
    • 7,281
    • PDF