A Systematic Approach to Batch Active Learning for Material Optimization
- 1Inst. Complex Molecular Systems, Dept. Biomedical Engineering, Eindhoven University of Technology
Abstract
Closed-loop automated experimentation platforms are accelerating materials characterization and discovery, but their efficiency hinges on a question that automation alone does not answer: given a fixed evaluation budget, which experiment configurations should be run next? Batch active learning addresses this by selecting a group of candidates at each iteration, yet the design choices that govern its efficiency, how many candidates to acquire per cycle, and how to balance exploitation against exploration remain poorly understood. Here, we present a systematic in-silico benchmark of batch active learning across optimization landscapes, prediction models, and dimensionalities, introducing composite metrics that track optimization progress and surrogate accuracy as co-equal outcomes. We find that an exploitative-dominant strategy with a small fixed exploratory minority matches or exceeds purely exploitative configurations while outperforming purely exploratory ones across landscapes, models, and dimensionalities, and that batchand cycle-efficient regimes are distinct and constraint-dependent. We further validate these findings on an automated coacervate condensate optimization platform, confirming their transfer to a real, noisy materials system.
Related
- Growth Profiles and Temporal Accumulation of Aniline-Blue-Reactive β-(1→3)-Glucan-Associated Material in Alcaligenes faecalis A12C Batch Cultures
- Metabolic Engineering and Bioprocess Optimization Strategies Promote l‑Azidohomoalanine Biosynthesis in Fed-Batch Bioreactor Culture
- Machine-Learning-Driven Performance Optimization of Nano-Modified Construction Materials: A Bibliometric Analysis and Systematic Review
- Case Study of Bayesian Batch Optimization Strategies for Heterogeneous Catalysts in CO2 Hydrogenation
- Manufacturing-conditioned hierarchical generation of cathode active-material microstructures with global electrode context
BibTeX
@misc{gardin2026systematic,
title = {{A Systematic Approach to Batch Active Learning for Material Optimization}},
author = {Andrea Gardin and Willem van den Hout and Yannick H. A. Leurs and Luc Brunsveld and JanC. M. van Hest and Francesca Grisoni},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15008883/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008883/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - A Systematic Approach to Batch Active Learning for Material Optimization
AU - Andrea Gardin
AU - Willem van den Hout
AU - Yannick H. A. Leurs
AU - Luc Brunsveld
AU - JanC. M. van Hest
AU - Francesca Grisoni
PY - 2026
DA - 2026/09/15
PB - ChemRxiv
DO - 10.26434/chemrxiv.15008883/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008883/v1
AB - Closed-loop automated experimentation platforms are accelerating materials characterization and discovery, but their efficiency hinges on a question that automation alone does not answer: given a fixed evaluation budget, which experiment configurations should be run next? Batch active learning addresses this by selecting a group of candidates at each iteration, yet the design choices that govern its efficiency, how many candidates to acquire per cycle, and how to balance exploitation against exploration remain poorly understood. Here, we present a systematic in-silico benchmark of batch active learning across optimization landscapes, prediction models, and dimensionalities, introducing composite metrics that track optimization progress and surrogate accuracy as co-equal outcomes. We find that an exploitative-dominant strategy with a small fixed exploratory minority matches or exceeds purely exploitative configurations while outperforming purely exploratory ones across landscapes, models, and dimensionalities, and that batchand cycle-efficient regimes are distinct and constraint-dependent. We further validate these findings on an automated coacervate condensate optimization platform, confirming their transfer to a real, noisy materials system.
ER -