Neural Optimal Design of Experiment for Inverse Problems
This work addresses the problem of designing efficient experiments for inverse problems in fields like medical imaging, offering a computationally simpler alternative to traditional methods.
The authors tackled the problem of optimal experimental design for inverse problems by introducing Neural Optimal Design of Experiments (NODE), which jointly trains a neural reconstruction model with continuous design variables to optimize measurement locations directly, avoiding classical bilevel optimization and indirect sparsity regularization. The approach outperformed baseline methods on benchmarks including MNIST image sampling and sparse-view X-ray CT, showing improved reconstruction accuracy and task-specific performance.
We introduce Neural Optimal Design of Experiments, a learning-based framework for optimal experimental design in inverse problems that avoids classical bilevel optimization and indirect sparsity regularization. NODE jointly trains a neural reconstruction model and a fixed-budget set of continuous design variables representing sensor locations, sampling times, or measurement angles, within a single optimization loop. By optimizing measurement locations directly rather than weighting a dense grid of candidates, the proposed approach enforces sparsity by design, eliminates the need for l1 tuning, and substantially reduces computational complexity. We validate NODE on an analytically tractable exponential growth benchmark, on MNIST image sampling, and illustrate its effectiveness on a real world sparse view X ray CT example. In all cases, NODE outperforms baseline approaches, demonstrating improved reconstruction accuracy and task-specific performance.