Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/88211
Title: | Distributed learning with minimum error entropy principle | Authors: | Guo, X Hu, T Wu, Q |
Issue Date: | 1-Aug-2019 | Source: | Paper presented at Joint Statistical Meetings (JSM2019), Denver, Colorado, Jul 27 - Aug 01, 2019 | Abstract: | Minimum Error Entropy (MEE) principle is an important approach in Information Theoretical Learning (ITL). It is widely applied and studied in various fields for its robustness to noise. In this paper, we study a reproducing kernel-based distributed MEE algorithm, DMEE, which is designed to work with both fully supervised data and semi-supervised data. With fully supervised data, our proved learning rates equal the minimax optimal learning rates of the classical pointwise kernel-based regressions. Under the semi-supervised learning scenarios, we show that DMEE exploits unlabeled data effectively, in the sense that first, under the settings with weaker regularity assumptions, additional unlabeled data significantly improves the learning rates of DMEE. Second, with sufficient unlabeled data, labeled data can be distributed to many more computing nodes, that each node takes only O(1) labels, without spoiling the learning rates in terms of the number of labels. | Keywords: | information theoretic learning Minimum error entropy Distributed method Semi-supervised data Reproducing kernel Hilbert space |
Rights: | Posted with permission of the author. |
Appears in Collections: | Presentation |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
DenverJSM2019Aug.pdf | 123.86 kB | Adobe PDF | View/Open |
Page views
96
Last Week
1
1
Last month
Citations as of Aug 25, 2024
Downloads
28
Citations as of Aug 25, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.