PATHFINDER: Designing Stimuli for Neuromodulation through data-driven inverse estimation of non-linear functions

TL;DR

PATHFINDER is a novel data-driven framework for designing neural stimuli by efficiently estimating inverse non-linear mappings, outperforming existing methods especially with limited data, which is crucial due to high costs of data collection.

Contribution

The paper introduces PATHFINDER, a new optimization framework that uses regression to estimate inverse mappings for stimulus design, addressing challenges of small sample sizes in neural response modeling.

Findings

PATHFINDER outperforms existing methods at small sample sizes.

It demonstrates high data-efficiency in biological neuron models.

The framework is effective for cost-sensitive stimulus design applications.

Abstract

There has been tremendous interest in designing stimuli (e.g. electrical currents) that produce desired neural responses, e.g., for inducing therapeutic effects for treatments. Traditionally, the design of such stimuli has been model-driven. Due to challenges inherent in modeling neural responses accurately, data-driven approaches offer an attractive alternative. The problem of data-driven stimulus design can be thought of as estimating an inverse of a non-linear ``forward" mapping, which takes in as inputs the stimulus parameters and outputs the corresponding neural responses. In most cases of interest, the forward mapping is many-to-one, and hence difficult to invert using traditional methods. Existing methods estimate the inverse by using conditional density estimation methods or numerically inverting an estimated forward mapping, but both approaches tend to perform poorly at small sample sizes. In this work, we develop a new optimization framework called PATHFINDER, which allows us to use regression methods for estimating an inverse mapping. We use toy examples to illustrate key aspects of PATHFINDER, and show, on computational models of biological neurons, that PATHFINDER can outperform existing methods at small sample sizes. The data-efficiency of PATHFINDER is especially valuable in stimulus design as collecting data is expensive in this domain.