# Distributed multi-task classification: a decentralized online learning approach

Distributed multi-task classification: a decentralized online learning approach Although dispersing one single task to distributed learning nodes has been intensively studied by the previous research, multi-task learning on distributed networks is still an area that has not been fully exploited, especially under decentralized settings. The challenge lies in the fact that different tasks may have different optimal learning weights while communication through the distributed network forces all tasks to converge to an unique classifier. In this paper, we present a novel algorithm to overcome this challenge and enable learning multiple tasks simultaneously on a decentralized distributed network. Specifically, the learning framework can be separated into two phases: (i) multi-task information is shared within each node on the first phase; (ii) communication between nodes then leads the whole network to converge to a common minimizer. Theoretical analysis indicates that our algorithm achieves a $$\mathcal {O}(\sqrt{T})$$ O ( T ) regret bound when compared with the best classifier in hindsight, which is further validated by experiments on both synthetic and real-world datasets. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Machine Learning Springer Journals

# Distributed multi-task classification: a decentralized online learning approach

, Volume 107 (4) – Nov 2, 2017
21 pages

Publisher
Springer Journals
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Control, Robotics, Mechatronics; Computing Methodologies; Simulation and Modeling; Language Translation and Linguistics
ISSN
0885-6125
eISSN
1573-0565
D.O.I.
10.1007/s10994-017-5676-y
Publisher site
See Article on Publisher Site

### Abstract

Although dispersing one single task to distributed learning nodes has been intensively studied by the previous research, multi-task learning on distributed networks is still an area that has not been fully exploited, especially under decentralized settings. The challenge lies in the fact that different tasks may have different optimal learning weights while communication through the distributed network forces all tasks to converge to an unique classifier. In this paper, we present a novel algorithm to overcome this challenge and enable learning multiple tasks simultaneously on a decentralized distributed network. Specifically, the learning framework can be separated into two phases: (i) multi-task information is shared within each node on the first phase; (ii) communication between nodes then leads the whole network to converge to a common minimizer. Theoretical analysis indicates that our algorithm achieves a $$\mathcal {O}(\sqrt{T})$$ O ( T ) regret bound when compared with the best classifier in hindsight, which is further validated by experiments on both synthetic and real-world datasets.

### Journal

Machine LearningSpringer Journals

Published: Nov 2, 2017

## You’re reading a free preview. Subscribe to read the entire article.

### DeepDyve is your personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month ### Explore the DeepDyve Library ### Search Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly ### Organize Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place. ### Access Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals. ### Your journals are on DeepDyve Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more. All the latest content is available, no embargo periods. DeepDyve ### Freelancer DeepDyve ### Pro Price FREE$49/month
\$360/year

Save searches from
PubMed

Create lists to

Export lists, citations