| Presentation | 2014-11-17 Multitask Learning Meets Tensor Factorization : Task Imputation via Convex Optimization Kishan WIMALAWARNE, Masashi SUGIYAMA, Ryota TOMIOKA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We study a multitask learning problem in which each task is parametrized by a weight vector and indexed by a pair of indices, which can be e.g, (consumer, time). The weight vectors can be collected into a tensor and the (multilinear-)rank of the tensor controls the amount of sharing of information among tasks. Two types of convex relaxations have recently been proposed for the tensor multilinear rank. However, we argue that both of them are not optimal in the context of multitask learning in which the dimensions or multilinear rank are typically inhomogeneous. We propose a new norm, which we call the scaled latent trace norm and analyze the excess risk of all the three norms. Both the theory and experiments support the advantage of the new norm when the tensor is not equal-sized and we do not a priori know which mode is low rank. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Multitask learning / scaled latent norm / tensor |
| Paper # | IBISML2014-49 |
| Date of Issue |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2014/11/10(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Information-Based Induction Sciences and Machine Learning (IBISML) |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Multitask Learning Meets Tensor Factorization : Task Imputation via Convex Optimization |
| Sub Title (in English) | |
| Keyword(1) | Multitask learning |
| Keyword(2) | scaled latent norm |
| Keyword(3) | tensor |
| 1st Author's Name | Kishan WIMALAWARNE |
| 1st Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology() |
| 2nd Author's Name | Masashi SUGIYAMA |
| 2nd Author's Affiliation | Department of Complexity Science and Engineering, University of Tokyo |
| 3rd Author's Name | Ryota TOMIOKA |
| 3rd Author's Affiliation | The Toyota Technological Institute at Chicago |
| Date | 2014-11-17 |
| Paper # | IBISML2014-49 |
| Volume (vol) | vol.114 |
| Number (no) | 306 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |