| 研究課題/領域番号 |
19K23193
|
|---|
| 研究機関 | 大阪大学 |
|---|
研究代表者 |
|
|---|
| 研究期間 (年度) |
2019-08-30 – 2023-03-31
|
| キーワード | High-dimensions / M-estimation / Sparsity |
|---|
| 研究実績の概要 |
The research was dedicated to the high-dimensional modelling of multivariate models that typically suffer from the "curse of dimensionality". The sparsity assumption is the main viewpoint: to identify the relevant model parameters, the sparse viewpoint allows to automatically select those parameters and perform feature extraction.
The objective of the modelling is to fix the over-fitting issue, the curse of dimensionality and to gain prediction accuracy for prediction purposes.
A significant part of the work was dedicated to the derivation of the theoretical properties of such high-dimensional techniques (asymptotic/finite sample properties) and to the assessment of the performances of such modelling through simulated and real data experiments.
The following works have been considered: high-dimensional modelling of multivariate stochastic volatility (MSV) models; sparse factor models; sparse estimation for copulas with pseudo-observations; non-linear feature selection and post-selection inference.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
1: 当初の計画以上に進展している
理由
Due to the sanitary situation arising from the spread of coronavirus-19, all face-to-face research conferences, seminars, meetings (both
domestic and international) have been cancelled. Thus, a part of the budget that was originally dedicated for
conference/seminars/research meetings has not been used.
Research progress is going well (3 international publications in 2021) and due to the broad range of open subjects and existing problems in the proposed research, new research papers are currently under development.
|
| 今後の研究の推進方策 |
Several projects within the area of the proposed research are currently under development. More precisely, the following works will be considered:
- sparse factor models, where we propose to develop an inferential framework to take into account the rotational indeterminacy constraint.
- the asymptotic properties of sparsity based estimators for copula models in the presence of pseudo-observations. The key challenge is to handle the non-parametric estimation of the marginals during the large sample analysis.
|
| 次年度使用額が生じた理由 |
Due to the spread of coronavirus 19, several international conferences and visiting research periods have been cancelled. We plan to use the budget for attending the conferences and purchasing a some equipments (workstation).
|
