Wang's research interests lie in the broad area of statistical machine learning — a research field that addresses the statistical and computational properties of machine learning algorithms and their optimality guarantees. Specifically, his work focuses on developing provable and practical methods for various challenging  learning regimes (e.g., high dimensional, heterogeneous, privacy-constrained, sequential, parallel and distributed) and often involves exploiting hidden structures in data (generalized sparsity, union-of-subspace, graph or network structures), balancing various resources (model complexity, statistical power and privacy budgets) as well as developing scalable optimization tools (e.g., those tailored for deep learning).