# Towards accelerating physical discovery via non-interactive and interactive multi-fidelity Bayesian Optimization: Current challenges and future opportunities

arXiv: https://arxiv.org/abs/2402.13402 · HTML: https://mlsanity.com/paper/2402.13402/

## Key facts

- Cited by 3 papers in the map (data through 7 Oct 2026).
- Builds on 5 of its 75 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 5 of 5)

- [Autonomous Materials Discovery Driven by Gaussian Process Regression with Inhomogeneous Measurement Noise and Anisotropic Kernels](https://mlsanity.com/paper/2006.02489/) (2020)
- [Autonomous optimization of nonaqueous battery electrolytes via robotic experimentation and machine learning](https://mlsanity.com/paper/2111.14786/) (2021)
- [Multi-fidelity machine-learning with uncertainty quantification and Bayesian optimization for materials design: Application to ternary random alloys](https://mlsanity.com/paper/2006.00139/) (2020)
- [Human-in-the-loop: The future of Machine Learning in Automated Electron Microscopy](https://mlsanity.com/paper/2310.05018/) (2023)
- [A dynamic Bayesian optimized active recommender system for curiosity-driven Human-in-the-loop automated experiments](https://mlsanity.com/paper/2304.02484/) (2023)

## Built on by (most cited first, 3 of 3)

- [SANE: Strategic Autonomous Non-Smooth Exploration for Multiple Optima Discovery in Multi-modal and Non-differentiable Black-box Functions](https://mlsanity.com/paper/2409.12295/) (2024)
- [Bayesian Co-navigation: Dynamic Designing of the Materials Digital Twins via Active Learning](https://mlsanity.com/paper/2404.12899/) (2024)
- [Measurements with Noise: Bayesian Optimization for Co-optimizing Noise and Property Discovery in Automated Experiments](https://mlsanity.com/paper/2410.02717/) (2024)

## Abstract (arXiv)

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and often non-differentiable parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of combinatorial libraries, processing spaces, and molecular embedding spaces. Often these systems are expensive or time-consuming to evaluate a single instance, and hence classical approaches based on exhaustive grid or random search are too data intensive. This resulted in strong interest towards active learning methods such as Bayesian optimization (BO) where the adaptive exploration occurs based on human learning (discovery) objective. However, classical BO is based on a predefined optimization target, and policies balancing exploration and exploitation are purely data driven. In practical settings, the domain expert can pose prior knowledge on the system in form of partially known physics laws and often varies exploration policies during the experiment. Here, we explore interactive workflows building on multi-fidelity BO (MFBO), starting with classical (data-driven) MFBO, then structured (physics-driven) sMFBO, and extending it to allow human in the loop interactive iMFBO workflows for adaptive and domain expert aligned exploration. These approaches are demonstrated over highly non-smooth multi-fidelity simulation data generated from an Ising model, considering spin-spin interaction as parameter space, lattice sizes as fidelity spaces, and the objective as maximizing heat capacity. Detailed analysis and comparison show the impact of physics knowledge injection and on-the-fly human decisions for improved exploration, current challenges, and potential opportunities for algorithm development with combining data, physics and real time human decisions.