Limits...
Sparse Zero-Sum Games as Stable Functional Feature Selection.

Sokolovska N, Teytaud O, Rizkalla S, MicroObese consortiumClément K, Zucker JD - PLoS ONE (2015)

Bottom Line: Feature selection, therefore, can lead not only to a problem with a reduced dimensionality, but also reveal some knowledge on functional classes of variables.In this contribution, we propose a framework based on a sparse zero-sum game which performs a stable functional feature selection.In particular, the approach is based on feature subsets ranking by a thresholding stochastic bandit.

View Article: PubMed Central - PubMed

Affiliation: Institute of Cardiometabolism and Nutrition, ICAN, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Paris, France; Sorbonne Universités, UPMC University Paris 6, UMR_S 1166, ICAN, NutriOmics Team, Paris, France; INSERM, UMR S U1166, NutriOmics Team, Paris, France.

ABSTRACT
In large-scale systems biology applications, features are structured in hidden functional categories whose predictive power is identical. Feature selection, therefore, can lead not only to a problem with a reduced dimensionality, but also reveal some knowledge on functional classes of variables. In this contribution, we propose a framework based on a sparse zero-sum game which performs a stable functional feature selection. In particular, the approach is based on feature subsets ranking by a thresholding stochastic bandit. We provide a theoretical analysis of the introduced algorithm. We illustrate by experiments on both synthetic and real complex data that the proposed method is competitive from the predictive and stability viewpoints.

No MeSH data available.


Experiments on the MicrObese transcriptomic data.On the left: accuracy; on the right: similarity on the level of separate genes.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4556702&req=5

pone.0134683.g008: Experiments on the MicrObese transcriptomic data.On the left: accuracy; on the right: similarity on the level of separate genes.

Mentions: Fig 8 above shows the accuracy of the t-test, a sparse SVM [39], the stochastic bandit, and the thresholding stochastic bandit. Below, on Fig 8 we demonstrate the genes similarity for these methods. Fig 9 shows the stability on the genes level and the functional stability on the genes level.


Sparse Zero-Sum Games as Stable Functional Feature Selection.

Sokolovska N, Teytaud O, Rizkalla S, MicroObese consortiumClément K, Zucker JD - PLoS ONE (2015)

Experiments on the MicrObese transcriptomic data.On the left: accuracy; on the right: similarity on the level of separate genes.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4556702&req=5

pone.0134683.g008: Experiments on the MicrObese transcriptomic data.On the left: accuracy; on the right: similarity on the level of separate genes.
Mentions: Fig 8 above shows the accuracy of the t-test, a sparse SVM [39], the stochastic bandit, and the thresholding stochastic bandit. Below, on Fig 8 we demonstrate the genes similarity for these methods. Fig 9 shows the stability on the genes level and the functional stability on the genes level.

Bottom Line: Feature selection, therefore, can lead not only to a problem with a reduced dimensionality, but also reveal some knowledge on functional classes of variables.In this contribution, we propose a framework based on a sparse zero-sum game which performs a stable functional feature selection.In particular, the approach is based on feature subsets ranking by a thresholding stochastic bandit.

View Article: PubMed Central - PubMed

Affiliation: Institute of Cardiometabolism and Nutrition, ICAN, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Paris, France; Sorbonne Universités, UPMC University Paris 6, UMR_S 1166, ICAN, NutriOmics Team, Paris, France; INSERM, UMR S U1166, NutriOmics Team, Paris, France.

ABSTRACT
In large-scale systems biology applications, features are structured in hidden functional categories whose predictive power is identical. Feature selection, therefore, can lead not only to a problem with a reduced dimensionality, but also reveal some knowledge on functional classes of variables. In this contribution, we propose a framework based on a sparse zero-sum game which performs a stable functional feature selection. In particular, the approach is based on feature subsets ranking by a thresholding stochastic bandit. We provide a theoretical analysis of the introduced algorithm. We illustrate by experiments on both synthetic and real complex data that the proposed method is competitive from the predictive and stability viewpoints.

No MeSH data available.