Back to Search
Start Over
Distributed learning and distribution regression of coefficient regularization
- Source :
- Journal of Approximation Theory. 263:105523
- Publication Year :
- 2021
- Publisher :
- Elsevier BV, 2021.
-
Abstract
- In this paper, we study the distributed learning algorithm and the distribution regression problem of coefficient regularization for Mercer kernels. By utilizing divided-and-conquer approach, we partition a data set into disjoint data subsets for different learning machines, and get the global estimator from local estimators. By using second order decomposition on the difference of operator inverse and properties of trace operator, we show that under some priori conditions of regression function, the result of distributed learning algorithm is as good as that in single batch data algorithm. On the other hand, we give a learning rate of distribution regression problem under the coefficient regularization scheme by using similar operator methods. We find that our learning scheme performs well when the regression function has stronger regularity. And we can see the deep relation of these two different problems.
- Subjects :
- Numerical Analysis
Applied Mathematics
General Mathematics
010102 general mathematics
Inverse
Estimator
010103 numerical & computational mathematics
Disjoint sets
01 natural sciences
Partition (database)
Regularization (mathematics)
Regression
Applied mathematics
Distributed learning
0101 mathematics
Analysis
Trace operator
Mathematics
Subjects
Details
- ISSN :
- 00219045
- Volume :
- 263
- Database :
- OpenAIRE
- Journal :
- Journal of Approximation Theory
- Accession number :
- edsair.doi...........222f4357408d1db559ff413c88fec757