Skip to main content

2017 | OriginalPaper | Buchkapitel

Lifelong Learning with Gaussian Processes

verfasst von : Christopher Clingerman, Eric Eaton

Erschienen in: Machine Learning and Knowledge Discovery in Databases

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Recent developments in lifelong machine learning have demonstrated that it is possible to learn multiple tasks consecutively, transferring knowledge between those tasks to accelerate learning and improve performance. However, these methods are limited to using linear parametric base learners, substantially restricting the predictive power of the resulting models. We present a lifelong learning algorithm that can support non-parametric models, focusing on Gaussian processes. To enable efficient online transfer between Gaussian process models, our approach assumes a factorized formulation of the covariance functions, and incrementally learns a shared sparse basis for the models’ parameterizations. We show that this lifelong learning approach is highly computationally efficient, and outperforms existing methods on a variety of data sets.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Álvarez, M.A., Lawrence, N.D.: Computationally efficient convolved multiple output Gaussian processes. J. Mach. Learn. Res. 12, 1459–1500 (2011)MathSciNetMATH Álvarez, M.A., Lawrence, N.D.: Computationally efficient convolved multiple output Gaussian processes. J. Mach. Learn. Res. 12, 1459–1500 (2011)MathSciNetMATH
2.
Zurück zum Zitat Álvarez, M.A., Luengo, D., Titsias, M.K., Lawrence, N.D.: Efficient multioutput Gaussian processes through variational inducing kernels. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 25–32 (2010) Álvarez, M.A., Luengo, D., Titsias, M.K., Lawrence, N.D.: Efficient multioutput Gaussian processes through variational inducing kernels. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 25–32 (2010)
3.
Zurück zum Zitat Bou Ammar, H., Eaton, E., Ruvolo, P., Taylor, M.E.: Online multi-task learning for policy gradient methods. In: Proceedings of the 31st International Conference on Machine Learning (ICML), June 2014 Bou Ammar, H., Eaton, E., Ruvolo, P., Taylor, M.E.: Online multi-task learning for policy gradient methods. In: Proceedings of the 31st International Conference on Machine Learning (ICML), June 2014
4.
Zurück zum Zitat Bonilla, E.V., Chai, K.M., Williams, C.: Multi-task Gaussian process prediction. In: Advances in Neural Information Processing Systems (NIPS), pp. 153–160 (2008) Bonilla, E.V., Chai, K.M., Williams, C.: Multi-task Gaussian process prediction. In: Advances in Neural Information Processing Systems (NIPS), pp. 153–160 (2008)
5.
Zurück zum Zitat Bou Ammar, H., Eaton, E., Luna, J.M., Ruvolo, P.: Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), July 2015 Bou Ammar, H., Eaton, E., Luna, J.M., Ruvolo, P.: Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), July 2015
6.
Zurück zum Zitat Bou Ammar, H., Tutunov, R., Eaton, E.: Safe policy search for lifelong reinforcement learning with sublinear regret. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), July 2015 Bou Ammar, H., Tutunov, R., Eaton, E.: Safe policy search for lifelong reinforcement learning with sublinear regret. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), July 2015
7.
Zurück zum Zitat Chalupka, K., Williams, C.K., Murray, I.: A framework for evaluating approximation methods for Gaussian process regression. J. Mach. Learn. Res. 14(1), 333–350 (2013)MathSciNetMATH Chalupka, K., Williams, C.K., Murray, I.: A framework for evaluating approximation methods for Gaussian process regression. J. Mach. Learn. Res. 14(1), 333–350 (2013)MathSciNetMATH
8.
Zurück zum Zitat Chen, Z., Liu, B.: Lifelong Machine Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, San Rafael (2016) Chen, Z., Liu, B.: Lifelong Machine Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, San Rafael (2016)
9.
Zurück zum Zitat Deisenroth, M., Ng, J.W.: Distributed Gaussian processes. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), pp. 1481–1490 (2015) Deisenroth, M., Ng, J.W.: Distributed Gaussian processes. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), pp. 1481–1490 (2015)
10.
Zurück zum Zitat Fei, G., Wang, S., Liu, B.: Learning cumulatively to become more knowledgeable. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016) Fei, G., Wang, S., Liu, B.: Learning cumulatively to become more knowledgeable. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)
12.
Zurück zum Zitat Isele, D., Luna, J.M., Eaton, E., Gabriel, V., Irwin, J., Kallaher, B., Taylor, M.E.: Lifelong learning for disturbance rejection on mobile robots. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2016) Isele, D., Luna, J.M., Eaton, E., Gabriel, V., Irwin, J., Kallaher, B., Taylor, M.E.: Lifelong learning for disturbance rejection on mobile robots. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2016)
13.
Zurück zum Zitat Kamar, E., Kapoor, A., Horvitz, E.: Lifelong learning for acquiring the wisdom of the crowd. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI) (2013) Kamar, E., Kapoor, A., Horvitz, E.: Lifelong learning for acquiring the wisdom of the crowd. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI) (2013)
14.
Zurück zum Zitat Kumar, A., Daumé III, H.: Learning task grouping and overlap in multi-task learning. In: Proceedings of the 29th International Conference on Machine Learning (ICML) (2012) Kumar, A., Daumé III, H.: Learning task grouping and overlap in multi-task learning. In: Proceedings of the 29th International Conference on Machine Learning (ICML) (2012)
15.
Zurück zum Zitat Maurer, A., Pontil, M., Romera-Paredes, B.: Sparse coding for multitask and transfer learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML), pp. 343–351, May 2013 Maurer, A., Pontil, M., Romera-Paredes, B.: Sparse coding for multitask and transfer learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML), pp. 343–351, May 2013
16.
Zurück zum Zitat Mitchell, T.M., Cohen, W.W., Talukdar, P.P., Betteridge, J., Carlson, A., Gardner, M., Kisiel, B., Krishnamurthy, J., et al.: Never ending learning. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence (2015) Mitchell, T.M., Cohen, W.W., Talukdar, P.P., Betteridge, J., Carlson, A., Gardner, M., Kisiel, B., Krishnamurthy, J., et al.: Never ending learning. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence (2015)
17.
Zurück zum Zitat Nguyen-Tuong, D., Peters, J.R., Seeger, M.: Local Gaussian process regression for real time online model learning. In: Advances in Neural Information Processing Systems (NIPS), pp. 1193–1200 (2009) Nguyen-Tuong, D., Peters, J.R., Seeger, M.: Local Gaussian process regression for real time online model learning. In: Advances in Neural Information Processing Systems (NIPS), pp. 1193–1200 (2009)
18.
Zurück zum Zitat Park, S., Choi, S.: Hierarchical Gaussian process regression. In: Proceedings of the 2nd Asian Conference on Machine Learning (ACML), pp. 95–110 (2010) Park, S., Choi, S.: Hierarchical Gaussian process regression. In: Proceedings of the 2nd Asian Conference on Machine Learning (ACML), pp. 95–110 (2010)
19.
Zurück zum Zitat Pentina, A., Urner, R.: Lifelong learning with weighted majority votes. In: Advances in Neural Information Processing Systems (NIPS), pp. 3612–3620 (2016) Pentina, A., Urner, R.: Lifelong learning with weighted majority votes. In: Advances in Neural Information Processing Systems (NIPS), pp. 3612–3620 (2016)
20.
Zurück zum Zitat Quinonero-Candela, J., Rasmussen, C.E.: A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6, 1939–1959 (2005)MathSciNetMATH Quinonero-Candela, J., Rasmussen, C.E.: A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6, 1939–1959 (2005)MathSciNetMATH
21.
Zurück zum Zitat Rakitsch, B., Lippert, C., Borgwardt, K., Stegle, O.: It is all in the noise: efficient multi-task Gaussian process inference with structured residuals. In: Advances in Neural Information Processing Systems (NIPS), pp. 1466–1474 (2013) Rakitsch, B., Lippert, C., Borgwardt, K., Stegle, O.: It is all in the noise: efficient multi-task Gaussian process inference with structured residuals. In: Advances in Neural Information Processing Systems (NIPS), pp. 1466–1474 (2013)
22.
Zurück zum Zitat Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2005) Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2005)
23.
Zurück zum Zitat Ruvolo, P., Eaton, E.: ELLA: an efficient lifelong learning algorithm. In: Proceedings of the 30th International Conference on Machine Learning (ICML), June 2013 Ruvolo, P., Eaton, E.: ELLA: an efficient lifelong learning algorithm. In: Proceedings of the 30th International Conference on Machine Learning (ICML), June 2013
24.
Zurück zum Zitat Snelson, E., Ghahramani, Z.: Sparse Gaussian processes using pseudo-inputs. In: Advances in Neural Information Processing Systems (NIPS), pp. 1257–1264 (2005) Snelson, E., Ghahramani, Z.: Sparse Gaussian processes using pseudo-inputs. In: Advances in Neural Information Processing Systems (NIPS), pp. 1257–1264 (2005)
25.
Zurück zum Zitat Thrun, S.: A lifelong learning perspective for mobile robot control. In: Proceedings of the IEEE/RSJ/GI International Conference on Intelligent Robots and Systems (IROS) ‘Advanced Robotic Systems and the Real World’ (1994) Thrun, S.: A lifelong learning perspective for mobile robot control. In: Proceedings of the IEEE/RSJ/GI International Conference on Intelligent Robots and Systems (IROS) ‘Advanced Robotic Systems and the Real World’ (1994)
26.
Zurück zum Zitat Tsanas, A., Little, M.A., McSharry, P.E., Ramig, L.O.: Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests. IEEE Trans. Biomed. Eng. 57(4), 884–893 (2010)CrossRef Tsanas, A., Little, M.A., McSharry, P.E., Ramig, L.O.: Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests. IEEE Trans. Biomed. Eng. 57(4), 884–893 (2010)CrossRef
27.
Zurück zum Zitat Wang, B., Pineau, J.: Generalized dictionary for multitask learning with boosting. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2016) Wang, B., Pineau, J.: Generalized dictionary for multitask learning with boosting. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2016)
29.
Zurück zum Zitat Yu, K., Tresp, V., Schwaighofer, A.: Learning Gaussian processes from multiple tasks. In: Proceedings of the 22nd International Conference on Machine Learning (ICML), pp. 1012–1019 (2005) Yu, K., Tresp, V., Schwaighofer, A.: Learning Gaussian processes from multiple tasks. In: Proceedings of the 22nd International Conference on Machine Learning (ICML), pp. 1012–1019 (2005)
Metadaten
Titel
Lifelong Learning with Gaussian Processes
verfasst von
Christopher Clingerman
Eric Eaton
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-71246-8_42