Abstract
Functional data is ubiquitous in many domains such as healthcare, social media, manufacturing process, sensor networks, etc. Functional data analysis involves the analysis of data which is treated as infinite-dimensional continuous functions rather than discrete, finite-dimensional vectors. In this paper, we propose a novel function-on-function regression model based on mode-sparsity regularization. The main idea is to represent the regression coefficient function between predictor and response as the double expansion of basis functions, and then use mode-sparsity constraint to automatically filter out the irrelevant basis functions for both predictors and responses. The mode-sparsity regularization covers a wide spectrum of sparse models for function-on-function regression. The resulting optimization problem is challenging due to the non-smooth property of the mode-sparsity. We develop an efficient and convergence-guaranteed algorithm to solve the problem. The effectiveness of the proposed approach is verified on benchmark functional data sets in various domains.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 16th IEEE International Conference on Data Mining, ICDM 2016 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1311-1316 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781509054725 |
| DOIs | |
| State | Published - Jan 31 2017 |
| Event | 16th IEEE International Conference on Data Mining, ICDM 2016 - Barcelona, Catalonia, Spain Duration: Dec 12 2016 → Dec 15 2016 |
Other
| Other | 16th IEEE International Conference on Data Mining, ICDM 2016 |
|---|---|
| Country | Spain |
| City | Barcelona, Catalonia |
| Period | 12/12/16 → 12/15/16 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
Functional regression with mode-sparsity constraint. / Yang, Pei; He, Jingrui.
Proceedings - 16th IEEE International Conference on Data Mining, ICDM 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1311-1316 7837991.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Functional regression with mode-sparsity constraint
AU - Yang, Pei
AU - He, Jingrui
PY - 2017/1/31
Y1 - 2017/1/31
N2 - Functional data is ubiquitous in many domains such as healthcare, social media, manufacturing process, sensor networks, etc. Functional data analysis involves the analysis of data which is treated as infinite-dimensional continuous functions rather than discrete, finite-dimensional vectors. In this paper, we propose a novel function-on-function regression model based on mode-sparsity regularization. The main idea is to represent the regression coefficient function between predictor and response as the double expansion of basis functions, and then use mode-sparsity constraint to automatically filter out the irrelevant basis functions for both predictors and responses. The mode-sparsity regularization covers a wide spectrum of sparse models for function-on-function regression. The resulting optimization problem is challenging due to the non-smooth property of the mode-sparsity. We develop an efficient and convergence-guaranteed algorithm to solve the problem. The effectiveness of the proposed approach is verified on benchmark functional data sets in various domains.
AB - Functional data is ubiquitous in many domains such as healthcare, social media, manufacturing process, sensor networks, etc. Functional data analysis involves the analysis of data which is treated as infinite-dimensional continuous functions rather than discrete, finite-dimensional vectors. In this paper, we propose a novel function-on-function regression model based on mode-sparsity regularization. The main idea is to represent the regression coefficient function between predictor and response as the double expansion of basis functions, and then use mode-sparsity constraint to automatically filter out the irrelevant basis functions for both predictors and responses. The mode-sparsity regularization covers a wide spectrum of sparse models for function-on-function regression. The resulting optimization problem is challenging due to the non-smooth property of the mode-sparsity. We develop an efficient and convergence-guaranteed algorithm to solve the problem. The effectiveness of the proposed approach is verified on benchmark functional data sets in various domains.
UR - http://www.scopus.com/inward/record.url?scp=85014531631&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85014531631&partnerID=8YFLogxK
U2 - 10.1109/ICDM.2016.68
DO - 10.1109/ICDM.2016.68
M3 - Conference contribution
SP - 1311
EP - 1316
BT - Proceedings - 16th IEEE International Conference on Data Mining, ICDM 2016
PB - Institute of Electrical and Electronics Engineers Inc.
ER -