AbstractThe modelling of many real-world problems relies on computationally heavy simulations. Since statistical inference rests on repeated simulations to sample the parameter space, the high computational expense of these simulations can become a stumbling block. In this paper, we compare two ways to mitigate this issue based on machine learning methods. One approach is to construct lightweight surrogate models to substitute the simulations used in inference. Alternatively, one might altogether circumnavigate the need for Bayesian sampling schemes and directly estimate the posterior distribution. We focus on stochastic simulations that track autonomous agents and present two case studies of real-world applications: tumour growths and the spread of infectious diseases. We demonstrate that good accuracy in inference can be achieved with a relatively small number of simulations, making our machine learning approaches orders of magnitude faster than classical simulation-based methods that rely on sampling the parameter space. However, we find that while some methods generally produce more robust results than others, no algorithm offers a one-size-fits-all solution when attempting to infer model parameters from observations. Instead, one must choose the inference technique with the specific real-world application in mind. The stochastic nature of the considered real-world phenomena poses an additional challenge that can become insurmountable for some approaches. Overall, we find machine learning approaches that create direct inference machines to be promising for real-world applications. We present our findings as general guidelines for modelling practitioners.Author summaryComputer simulations play a vital role in modern science as they are commonly used to compare theory with observations. One can thus infer the properties of a observed system by comparing the data to the predicted behaviour in different scenarios. Each of these scenarios corresponds to a simulation with slightly different settings. However, since real-world problems are highly complex, the simulations often require extensive computational resources, making direct comparisons with data challenging, if not insurmountable. It is, therefore, necessary to resort to inference methods that mitigate this issue, but it is not clear-cut what path to choose for any specific research problem. In this paper, we provide general guidelines for how to make this choice. We do so by studying examples from oncology and epidemiology and by taking advantage of developments in machine learning. More specifically, we focus on simulations that track the behaviour of autonomous agents, such as single cells or individuals. We show that the best way forward is problem-dependent and highlight the methods that yield the most robust results across the different case studies. We demonstrate that these methods are highly promising and produce reliable results in a small fraction of the time required by classic approaches that rely on comparisons between data and individual simulations. Rather than relying on a single inference technique, we recommend employing several methods and selecting the most reliable based on predetermined criteria.
Handrails through the Swamp? A Pilot to Test the Integration and Implementation Science Framework in Complex Real-World Research
