Nature

Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems

Algorithms have become ubiquitous in modern life 1, with numerous applications in fields ranging from finance and business to healthcare and transportation. They are essential tools for making sense ...
Nature

Optimal control of discrete event systems under uncertain environment based on supervisory control theory and reinforcement learning

Discrete event systems (DESs) are powerful abstract representations for large human-made physical systems in a wide variety of industries. Safety control issues on DESs have been extensively studied ...