Random field optimization

• Present modeling abstraction that we call random field optimization. Abstraction captures uncertainty lives on continuous space-time domains. Demonstrate the applicability using case studies. We present a new paradigm for optimization Random fields are powerful aims to capture behavior of variables live infinite-dimensional spaces (e.g., space and time) such as stochastic processes time series, Gaussian processes, Markov processes), matrices, spatial fields. This involves sophisticated mathematical objects differential equations kernel functions) has been widely used in neuroscience, geoscience, physics, civil engineering, computer graphics. Despite this, however, have seen limited use optimization; specifically, existing paradigms involve programming robust optimization) mostly focus finite variables. trend is rapidly changing with advent statistical Bayesian multi-scale integration molecular sciences process engineering). Our work extends recently-proposed problems by capturing more general representations. Moreover, discuss solution this class based transformations sampling, identify open questions challenges.