Summit: Benchmarking Machine Learning Methods for Reaction Optimisation

Felton, Kobi; Rittig, Jan G.; Lapkin, Alexei A.

doi:10.26434/chemrxiv.12939806.v2

Cited by 19 publications

(25 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Reizman-Suzuki represents virtual experiments for the Suzuki-Miyaura Cross-Coupling reaction where experimental outcomes are based on an emulator that is trained on the experimental data published by [34]. The experimental emulator is provided by [13] and outputs product yield and catalyst turnover number as objectives to be maximised. This optimisation problem consists of three continuous variables (d x = 3): temperature, residence time and catalyst loading; and one categorical variable (k = 1): catalyst choice (8 possible combinations).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian Optimisation for Mixed-Variable Inputs using Value Proposals

Zuo¹,

Dezfouli²,

Chadès³

et al. 2022

Preprint

View full text Add to dashboard Cite

Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such as Bayesian Optimisation (BO) are not designed to handle such mixedvariable search spaces. Recent approaches to this problem cast the selection of the categorical variables as a bandit problem, operating independently alongside a BO component which optimises the continuous variables. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We derive candidates from the Expected Improvement criterion, which we call value proposals, and use these proposals to make selections on both the categorical and continuous components of the input. We show that this unified approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.

show abstract

Section: Methodsmentioning

confidence: 99%

“…• Baumgartner represents virtual experiments for the Aniline Cross-Coupling reaction where experimental outcomes are based on an emulator that is trained on the experimental data published by [2]. The experimental emulator is provided by [13] and outputs product yield and material cost as objectives to be maximised and minimised respectively.…”

Section: Methodsmentioning

confidence: 99%

Bayesian Optimisation for Mixed-Variable Inputs using Value Proposals

Zuo¹,

Dezfouli²,

Chadès³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Where I c is the index set of the control variables. We implement the simulation using the Summit package [Felton et al, 2021]. We control temperature between 40 and 120 degrees, and concentration from 0.1 to 0.5 moles per liter.…”

Section: Reaction Control On Snar Benchmarkmentioning

confidence: 99%

SnAKe: Bayesian Optimization with Pathwise Exploration

Folch¹,

Zhang²,

M³

et al. 2022

Preprint

View full text Add to dashboard Cite

Bayesian Optimization is a very effective tool for optimizing expensive black-box functions. Inspired by applications developing and characterizing reaction chemistry using droplet microfluidic reactors, we consider a novel setting where the expense of evaluating the function can increase significantly when making large input changes between iterations. We further assume we are working asynchronously, meaning we have to decide on new queries before we finish evaluating previous experiments. This paper investigates the problem and introduces 'Sequential Bayesian Optimization via Adaptive Connecting Samples' (SnAKe), which provides a solution by considering future queries and preemptively building optimization paths that minimize input costs. We investigate some convergence properties and empirically show that the algorithm is able to achieve regret similar to classical Bayesian Optimization algorithms in both the synchronous and asynchronous settings, while reducing the input costs significantly.

show abstract

“…An optimization campaign thus typically proceeds by iteratively testing sets of parameters x, as defined via a design of experiment or as suggested by an experiment planning algorithm [25][26][27] . Common design of experiment approaches rely on random or systematic searches of parameter combinations.…”

Section: Background and Related Workmentioning

confidence: 99%