Materials Science Optimization Benchmark Dataset for High-dimensional, Multi-objective, Multi-fidelity Optimization of CrabNet Hyperparameters

• Published in: ChemRxiv
• Main Authors: Baird, Sterling G., Parikh, Jeet N., Sparks, Taylor D.
• Format: Paper
• Language: English
• Published: Washington American Chemical Society 07.03.2023
• Edition: 1
• Subjects: Accuracy; Benchmarks; Chemistry; Datasets; Energy gap; Materials Science; Multiple objective analysis; Optimization; Random noise; Run time (computers); Simulation; Task complexity; formulation optimization; Bayesian optimization; adaptive design; PseudoCrab

Benchmarks are crucial for driving progress in scientific disciplines. To be effective, benchmarks should closely mimic real-world tasks while being computationally efficient, allowing for accessibility and repeatability. Developing surrogate models that can be indistinguishable from the ground trut...