Abstract
Bayesian optimisation is an efficient technique to optimise functions that are expensive to compute. In this paper, we propose a novel framework to transfer knowledge from a completed source optimisation task to a new target task in order to overcome the cold start problem. We model source data as noisy observations of the target function. The level of noise is computed from the data in a Bayesian setting. This enables flexible knowledge transfer across tasks with differing relatedness, addressing a limitation of the existing methods. We evaluate on the task of tuning hyperparameters of two machine learning algorithms. Treating a fraction of the whole training data as source and the whole as the target task, we show that our method finds the best hyperparameters in the least amount of time compared to both the state-of-art and no transfer method.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Advances in neural information processing systems, pp. 2951–2959 (2012)
Mockus, J.: Application of Bayesian approach to numerical methods of global and stochastic optimization. J. Global Optim. 4(4), 347–365 (1994)
Lizotte, D.J., Wang, T., Bowling, M.H., Schuurmans, D.: Automatic gait optimization with Gaussian process regression. IJCAI 7, 944–949 (2007)
Brochu, E., Cora, V.M., De Freitas, N.: A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning (2010). arXiv preprint arXiv:1012.2599
Garnett, R., Osborne, M.A., Roberts, S.J.: Bayesian optimization for sensor set selection. In: Proceedings of the 9th ACM/IEEE International Conference on Information Processing in Sensor Networks, pp. 209–219. ACM (2010)
Bergstra, J., Bardenet, R., Kégl, B., Bengio, Y.: Implementations of algorithms for hyper-parameter optimization. In: NIPS Workshop on Bayesian Optimization, p. 29 (2011)
Thornton, C., Hutter, F., Hoos, H.H., Leyton-Brown, K.: Auto-weka: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 847–855. ACM (2013)
Bardenet, R., Brendel, M., Kégl, B., et al.: Collaborative hyperparameter tuning. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), pp. 199–207 (2013)
Yogatama, D., Mann, G.: Efficient transfer learning method for automatic hyperparameter tuning. Transfer 1, 1 (2014)
Williams, C.K., Rasmussen, C.E.: Gaussian Processes for Machine Learning, vol. 2, 3rd edn. The MIT Press, Cambridge (2006)
Kushner, H.J.: A new method of locating the maximum point of an arbitrary multipeak curve in the presence of noise. J. Fluids Eng. 86(1), 97–106 (1964)
Mockus, J., Tiesis, V., Zilinskas, A.: The application of bayesian methods for seeking the extremum. Towards Global Optim. 2(117–129), 2 (1978)
Srinivas, N., Krause, A., Kakade, S., Seeger, M.: Gaussian process optimization in the bandit setting: no regret and experimental design. In: Proceedings of International Conference on Machine Learning (ICML) (2010)
Chang, C.-C., Lin, C.-J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Joy, T.T., Rana, S., Gupta, S.K., Venkatesh, S. (2016). Flexible Transfer Learning Framework for Bayesian Optimisation. In: Bailey, J., Khan, L., Washio, T., Dobbie, G., Huang, J., Wang, R. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2016. Lecture Notes in Computer Science(), vol 9651. Springer, Cham. https://doi.org/10.1007/978-3-319-31753-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-31753-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-31752-6
Online ISBN: 978-3-319-31753-3
eBook Packages: Computer ScienceComputer Science (R0)