Joint Surrogate Learning of Objectives, Constraints, and Sensitivities for Efficient Multi-objective Optimization of Neural Dynamical Systems

TL;DR

The paper introduces DMOSOPT, a scalable surrogate-based optimization framework that efficiently navigates high-dimensional, constrained parameter spaces in neural system simulations by jointly modeling objectives, constraints, and sensitivities.

Contribution

It presents a novel joint surrogate model that captures the interplay of objectives, constraints, and sensitivities, enabling more efficient multi-objective optimization in complex neural systems.

Findings

Efficient optimization with fewer evaluations at supercomputing scale.

Effective handling of high-dimensional, constrained problems.

Applicable across various scientific and engineering domains.

Abstract

Biophysical neural system simulations are among the most computationally demanding scientific applications, and their optimization requires navigating high-dimensional parameter spaces under numerous constraints that impose a binary feasible/infeasible partition with no gradient signal to guide the search. Here, we introduce DMOSOPT, a scalable optimization framework that leverages a unified, jointly learned surrogate model to capture the interplay between objectives, constraints, and parameter sensitivities. By learning a smooth approximation of both the objective landscape and the feasibility boundary, the joint surrogate provides a unified gradient that simultaneously steers the search toward improved objective values and greater constraint satisfaction, while its partial derivatives yield per-parameter sensitivity estimates that enable more targeted exploration. We validate the framework from single-cell dynamics to population-level network activity, spanning incremental stages of a neural circuit modeling workflow, and demonstrate efficient, effective optimization of highly constrained problems at supercomputing scale with substantially fewer problem evaluations. While motivated by and demonstrated in the context of computational neuroscience, the framework is general and applicable to constrained multi-objective optimization problems across scientific and engineering domains.