Local Multidimensional Scaling with Controlled Tradeoff Between Trustworthiness and Continuity

In a visualization task, every nonlinear projection method needs to make a compromise between trustworthiness and continuity. In a trustworthy projection the visualized proximities hold in the original data as well, whereas a continuous projection visualizes all proximities of the original data. A multidimensional scaling method, curvilinear components analysis, is good at maximizing trustworthiness. We extend it to explicitly make a user-tunable parameterized compromise between trustworthiness and continuity.