Dejun Chu — accepted AI-conference papers

2023

Structured BFGS Method for Optimal Doubly Stochastic Matrix Approximation

Dejun Chu, Changshui Zhang, Shiliang Sun, Qing Tao

AAAI 2023technical

Doubly stochastic matrix plays an essential role in several areas such as statistics and machine learning. In this paper we consider the optimal approximation of a square matrix in the set of doubly stochastic matrices. A structured BFGS method is proposed to solve the dual of the primal problem. Th…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2020

Semismooth Newton Algorithm for Efficient Projections onto $\ell_1, ∞$-norm Ball

Dejun Chu, Changshui Zhang, Shiliang Sun, Qing Tao

ICML 2020poster

The structured sparsity-inducing $\ell_{1, \infty}$-norm, as a generalization of the classical $\ell_1$-norm, plays an important role in jointly sparse models which select or remove simultaneously all the variables forming a group. However, its resulting problem is more difficult to solve than the c…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗