# Closed-loop discovery of out-of-distribution processing protocols by evolutionary search and uncertainty-aware learning

arXiv: https://arxiv.org/abs/2606.13859 · HTML: https://mlsanity.com/paper/2606.13859/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 45 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Deep Kernel Methods Learn Better: From Cards to Process Optimization](https://mlsanity.com/paper/2303.14554/) (2023)
- [Reward driven workflows for unsupervised explainable analysis of phases and ferroic variants from atomically resolved imaging data](https://mlsanity.com/paper/2411.12612/) (2024)
- [Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model](https://mlsanity.com/paper/2503.02978/) (2025)
- [Rapid optimization in high dimensional space by deep kernel learning augmented genetic algorithms](https://mlsanity.com/paper/2410.03173/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Closed-Loop Optimization to Open Decision Making: Coupled Digital Twins for Predictive and Autonomous Microscopy](https://mlsanity.com/paper/2607.05758/) (2026)

## Abstract (arXiv)

Many materials and chemical systems exhibit history-dependent responses, where functional outcomes are governed not only by final-state variables but by the time-dependent sequence of fields, temperatures, or chemical potentials applied during operation. Discovering new processing protocols is therefore a high-dimensional search problem in which the control variable is an entire waveform or sample history, and conventional strategies either remain confined to conservative interpolative families or become prohibitively measurement intensive. Here, a closed-loop workflow is introduced that couples evolutionary search over a compact waveform representation with uncertainty-aware deep kernel learning to generate, rank, and experimentally validate candidate protocols. Applied to ferroelectric thin films, with the scanning-probe tip-bias waveform as the protocol and the nonlinear electromechanical response as the reward, the workflow discovers waveform families that enhance nonlinearity by de-aging the film. Spatially resolved before/after measurements show that the best-performing waveforms selectively activate pre-existing, weakly pinned domain-wall segments, whereas the worst drive long-range irreversible switching. This framework reframes protocol tuning as out-of-distribution discovery, generalizable to synthesis and annealing trajectories, battery formation protocols, and other high-dimensional control problems.