| Presentation | 2014-11-17 Efficient leave-one-out cross-validation for L2-regularized classifier Shota OKUMURA, Yoshiki SUZUKI, Kohei OGAWA, Yuki SHINMURA, Ichiro TAKEUCHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Leave-one-out cross-validation (LOOCV) is a useful tool for estimating generalization performances of various machine learning algorithms. However, except for some special cases, computing LOOCV error is quite time-consuming because we must train as many models as the number of instances. In this study, we propose an efficient method for LOOCV of L_2-regularized convex binary classification algorithms. The proposed method allows us to make decisions on whether the left-out instance is correctly classified or not before actually solving the optimization problem. The proposed approach can be applicable to wider class of problems than existing approaches and it can also be used as a stopping criterion in the optimization process. We illustrate the advantage of the proposed method based on numerical experiments. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | cross-validation / convex optimization / model selection / support vector machine |
| Paper # | IBISML2014-44 |
| 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 | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Efficient leave-one-out cross-validation for L2-regularized classifier |
| Sub Title (in English) | |
| Keyword(1) | cross-validation |
| Keyword(2) | convex optimization |
| Keyword(3) | model selection |
| Keyword(4) | support vector machine |
| 1st Author's Name | Shota OKUMURA |
| 1st Author's Affiliation | Department of Engineering, Nagoya Institute of Technology() |
| 2nd Author's Name | Yoshiki SUZUKI |
| 2nd Author's Affiliation | Department of Engineering, Nagoya Institute of Technology |
| 3rd Author's Name | Kohei OGAWA |
| 3rd Author's Affiliation | Department of Engineering, Nagoya Institute of Technology |
| 4th Author's Name | Yuki SHINMURA |
| 4th Author's Affiliation | Department of Engineering, Nagoya Institute of Technology |
| 5th Author's Name | Ichiro TAKEUCHI |
| 5th Author's Affiliation | Department of Engineering, Nagoya Institute of Technology |
| Date | 2014-11-17 |
| Paper # | IBISML2014-44 |
| Volume (vol) | vol.114 |
| Number (no) | 306 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |