Jun Wang

TL;DR: In this article, a low-rank linearized SVM (LRLSVM) is proposed to scale up kernel SVM on limited resources, which transforms a nonlinear SVM to a linear one via an approximate empirical kernel map computed from efficient kernel low rank decompositions and theoretically analyzes the gap between the solutions of the approximate and optimal rank- $k$ kernel map, which in turn provides guidance on the sampling scheme of the Nystrom approximation.

TL;DR: A novel online algorithm is presented that leverages Thompson sampling into the sequential decision-making process for portfolio blending and sequentially determines the optimal coefficients to blend multiple portfolios that embody different criteria of investment and market views.

TL;DR: A novel multi-view registration method, where the optimal registration is achieved via an efficient and effective alternating concave minimization process, that outperforms peer point matching methods and performs competitively against graph matching approaches.

TL;DR: An approximate dynamic programing method of synergistically combining the Lowner-John ellipsoid approximation with conventional value function iteration to quantify the associated optimal trading policy and cut computational costs up to a factor of five hundred is developed.