Harold Joseph Kushner is an American applied mathematician and a Professor Emeritus of Applied Mathematics at Brown University. He is known for his work on the theory of stochastic stability (based on the concept of supermartingales as Lyapunov functions), the theory of non-linear filtering (based on the Kushner equation), and for the development of numerical methods for stochastic control problems such as the Markov chain approximation method. He is commonly cited as the first person to study Bayesian optimization,[1][2] based on work he published in 1964.[3]
^Brochu, Eric; Cora, Vlad M.; de Freitas, Nando (12 December 2010). "A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning". arXiv:1012.2599 [cs.LG].