Qingsong Wang

Qingsong Wang works on mathematical optimization methods for large-scale data problems, especially algorithms for decomposing tensors and matrices (ways of breaking complex multi-dimensional data into simpler components) and for training neural networks. Much of the work develops faster, more efficient optimization algorithms (such as stochastic, inertial, and proximal methods) and applies them to tasks like image denoising, medical image enhancement, and geometric data analysis.

Publication output has grown substantially over the last decade, rising from about 1-2 papers per year before 2020 to 8-11 per year in 2024-2025.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026