Flexible and efficient simulation-based inference for models of decision-making

Abstract

Inferring parameters of computational models that capture experimental data is a central task in cognitive neuroscience. Bayesian statistical inference methods usually require the ability to evaluate the likelihood of the model--however, for many models of interest in cognitive neuroscience, the associated likelihoods cannot be computed effciently. Simulation-based inference (SBI) offers a solution to this problem by only requiring access to simulations produced by the model. Here, we provide an effcient SBI method for models of decision-making. Our approach, Mixed Neural Likelihood Estimation (MNLE), trains neural density estimators on model simulations to emulate the simulator, and is designed to capture both the continuous (e.g., reaction times) and discrete (choices) data of decision-making models. The likelihoods of the emulator can then be used to perform Bayesian parameter inference on experimental data using standard approximate inference methods like Markov Chain Monte Carlo sampling. We demonstrate MNLE on two variants of the drift-diffusion model (DDM) and compare its performance to a recently proposed method for SBI on DDMs, called Likelihood Approximation Networks (LANs, Fengler et al. 2021). We show that MNLE is substantially more effcient than LANs: it achieves similar likelihood accuracy with six orders of magnitude fewer training simulations, and is substantially more accurate than LANs when both are trained with the same budget. This enables researchers to train MNLE on custom-tailored models of decision-making, leading to fast iteration of model design for scientific discovery.