ResearchModeling Techniques for Graph LearningWe develop mathematical tools for learning the graph structure from data without observing edges of the graph. It is a crucial problem in many disciplines of data science. We achieve the goal by adopting modeling techniques from graph signal processing and physics-inspired nonlinear dynamics models. The rigorous theoretical aspects of our developed methods are particularly emphasized, where our work demonstrated that they can reliably recover the correct structure from a provable lower bound on the amount of data. Checkout the publications for more details. Optimization for Large-scale Machine Learning and Signal ProcessingWe study algorithms for large scale machine learning and information processing in order to handle the challenges with ‘big-data‘. We focus on two interconnected aspects: first we study algorithms that run on inter-connected agents’ system such that the computation burden can be distributed evenly across the network; second we study algorithms that feed on stochastic (e.g., streaming or dynamical) data. In both cases, we provide rigorous analysis on the performance with convex and non-convex optimization models. Checkout the publications for more details. |