Abstract
We analyse the dynamics of gradient-based learning algorithms using the cavity method, considering the cases of batch learning with non-vanishing rates, and on-line learning. It has an an excellent agreement with simulations. Applications to efficient and precise estimation of hyperparameters are proposed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Saad, D. (ed.): On-line learning in Neural Networks. Cambridge University Press, Cambridge (1998)
Wong, K.Y.M., Li, S., Tong, Y.W.: Many-body approach to the dynamics of batch learning. Phys. Rev. E 62, 4036–4042 (2000)
Luo, P., Wong, K.Y.M.: Dynamical and stationary properties of on-line learning from finite training sets. Phys. Rev. E 67, 11906 (2003) (to appear)
Bös, S., Opper, M.: Dynamics of batch learning in a perceptron. J. Phys. A 31, 4835–4850 (1998)
Barber, D., Sollich, P.: Online learning from finite training sets, in [1], 279– 302 (1998)
Heimel, J.A.F., Coolen, A.C.C.: Supervised learning with restricted training sets: a generating functional analysis. J. Phys. A: Math. Gen. 34, 9009–9026 (2001)
Amari, S., Murata, N., Müller, K.-R., Finke, M., Yang, H.H.: Asymptotic statisitcal theory of overtraining and cross-validation. IEEE Trans. on Neural Networks 8, 985–996 (1997)
Wong, K.Y.M., Li, F.: Fast parameter estimation using Green’s functions. In: Dieterrich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems 14. MIT Press, Cambridge (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wong, K.Y.M., Luo, P., Li, F. (2003). Dynamics of Gradient-Based Learning and Applications to Hyperparameter Estimation. In: Liu, J., Cheung, Ym., Yin, H. (eds) Intelligent Data Engineering and Automated Learning. IDEAL 2003. Lecture Notes in Computer Science, vol 2690. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45080-1_48
Download citation
DOI: https://doi.org/10.1007/978-3-540-45080-1_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40550-4
Online ISBN: 978-3-540-45080-1
eBook Packages: Springer Book Archive