Journal
SCIENCE CHINA-MATHEMATICS
Volume 63, Issue 11, Pages 2233-2266Publisher
SCIENCE PRESS
DOI: 10.1007/s11425-020-1773-8
Keywords
machine learning; continuous formulation; flow-based model; gradient flow; particle approximation
Categories
Funding
- Office of Naval Research (ONR) Grant [N00014-13-1-0338]
- iFlytek
Ask authors/readers for more resources
We present a continuous formulation of machine learning, as a problem in the calculus of variations and differential-integral equations, in the spirit of classical numerical analysis. We demonstrate that conventional machine learning models and algorithms, such as the random feature model, the two-layer neural network model and the residual neural network model, can all be recovered (in a scaled form) as particular discretizations of different continuous formulations. We also present examples of new models, such as the flow-based random feature model, and new algorithms, such as the smoothed particle method and spectral method, that arise naturally from this continuous formulation. We discuss how the issues of generalization error and implicit regularization can be studied under this framework.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available