Name
Abstract | ||
|---|---|---|
A series of online multi-task learning (OMTL) algorithms have been proposed to avoid the expensive training cost and poor adaptability of traditional batch multi-task learning (MTL) algorithms in recent years. However, these OMTL algorithms usually assume that all tasks are closely related, which may not hold in practical scenarios. More importantly, their theoretical reliability is weakened due to the lack of proof on the cumulative regrets. To overcome these limitations, we present a robust online multi-task classification framework (ROM) and its two optimization algorithms (ROM-PGD, ROM-RDA). The proposed algorithms can not only automatically capture the common features among all tasks and individual features for each task, but also identify the potential existence of outlier task. Theoretically, we prove that the regret bounds of these two algorithms are sub-linear compared with the best separating algorithm in hindsight. Empirical studies on both synthetic and real-world datasets also demonstrate the effectiveness of our proposed algorithms when compared with the state-of-the-art OMTL algorithms. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/ICDM.2016.45 | 2016 IEEE 16TH INTERNATIONAL CONFERENCE ON DATA MINING (ICDM) |
Field | DocType | ISSN |
Analysis of parallel algorithms,Data mining,Multi-task learning,Algorithm design,Regret,Computer science,Outlier,Probabilistic analysis of algorithms,Robustness (computer science),Artificial intelligence,Quality control and genetic algorithms,Machine learning | Conference | 1550-4786 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chi Zhang | 1 | 6 | 1.78 |
| Peilin Zhao | 2 | 1365 | 80.09 |
| Shuji Hao | 3 | 110 | 6.57 |
| Yeng Chai Soh | 4 | 1777 | 155.44 |
| Bu Sung Lee | 5 | 452 | 35.22 |