← Search

Jason Ge

2 accepted papers

2018

Minimax-Optimal Privacy-Preserving Sparse PCA in Distributed Systems

AISTATS 2018poster

This paper proposes a distributed privacy-preserving sparse PCA (DPS-PCA) algorithm that generates a minimax-optimal sparse PCA estimator under differential privacy constraints. In a distributed optimization framework, data providers can use this algorithm to collaboratively analyze the union of the…

Cited by 0SourcePDFScholar
2017

On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning

NeurIPS 2017poster

We propose a DC proximal Newton algorithm for solving nonconvex regularized sparse learning problems in high dimensions. Our proposed algorithm integrates the proximal newton algorithm with multi-stage convex relaxation based on the difference of convex (DC) programming, and enjoys both strong comp…

Cited by 16SourcePDFScholar