Lanfan Jiang

Bio: Lanfan Jiang is an academic researcher from Center for Discrete Mathematics and Theoretical Computer Science. The author has contributed to research in topics: Optimization problem & Group method of data handling. The author has an hindex of 1, co-authored 2 publications receiving 1 citations.

Weighted thresholding homotopy method for sparsity constrained optimization

Abstract: We propose in this paper a novel weighted thresholding method for the sparsity-constrained optimization problem. By reformulating the problem equivalently as a mixed-integer programming, we investigate the Lagrange duality with respect to an $$l_1$$-norm constraint and show the strong duality property. Then we derive a weighted thresholding method for the inner Lagrangian problem, and analyze its convergence. In addition, we give an error bound of the solution under some assumptions. Further, based on the proposed method, we develop a homotopy algorithm with varying sparsity level and Lagrange multiplier, and prove that the algorithm converges to an L-stationary point of the primal problem under some conditions. Computational experiments show that the proposed algorithm is competitive with state-of-the-art methods for the sparsity-constrained optimization problem.

Two-Stage Neural Network Classifier for the Data Imbalance Problem with Application to Hotspot Detection

Abstract: The data imbalance problem often occurs in nanometer VLSI applications, where normal cases far outnumber error ones. Many imbalanced data handling methods have been proposed, such as oversampling minority class samples and downsampling majority class samples. However, existing methods focus on improving the quality of minority classes while causing quality deterioration of majority ones. In this paper, we propose a two-stage classifier to handle the data imbalance problem. We first develop an iterative neural network framework to reduce false alarms. Then the oversampling method on a final classification network is applied to predict the two classes better. As a result, the data imbalance problem is well handled, and the quality deterioration of majority classes is also reduced. Since the iterative stage does not change any existing network structure, any convolutional neural network can be used in the framework. Compared with the state-of-the-art imbalanced data handling methods, experimental results on the hotspot detection problem show that our two-stage classification method achieves the best prediction accuracy and reduces false alarms significantly.

Sparse Group Feature Selection by Weighted Thresholding Homotopy Method

Abstract: In this paper, we investigate the sparse group feature selection problem, in which covariates posses a grouping structure sparsity at the level of both features and groups simultaneously. We reformulate the feature sparsity constraint as an equivalent weighted $l_1$ -norm constraint in the sparse group optimization problem. To solve the reformulated problem, we first propose a weighted thresholding method based on a dynamic programming algorithm. Then we improve the method to a weighted thresholding homotopy algorithm using homotopy technique. We prove that the algorithm converges to an $L$ -stationary point of the original problem. Computational experiments on synthetic data show that the proposed algorithm is competitive with some state-of-the-art algorithms.