Bayesian optimisation for efficient material discovery: a mini review.

Bayesian optimisation (BO) has been increasingly utilised to guide material discovery. While BO is advantageous due to its sample efficiency, flexibility and versatility, it is constrained by a range of core issues including high-dimensional optimisation, mixed search space, multi-objective optimisation and multi-fidelity data. Although various studies have attempted to tackle one or some challenges, a comprehensive BO framework for material discovery is yet to be uncovered. This work provides a short review aiming at connecting algorithmic advancement to material applications. Open algorithmic challenges are discussed and supported by recent material applications. Various open-source packages are compared to assist the selection. Furthermore, three exemplary material design problems are analysed to demonstrate how BO could be useful. The review concludes with an outlook on BO-aided autonomous laboratory.

The framing of choice nudges prolonged processing in the evaluation of food images.

Previous research suggests that the type of choice framing for evaluation tasks can influence the relationship between response time and preference-based decision-making. Two separable factors may modulate the preference-based decision-making: The set of choice options (with or without an option to defer) and the constraint of choice (with high or low maximum for inclusion). To clarify how these factors influence the process of preference-based decision-making, we designed a virtual-shopping paradigm with a series of food images presented consecutively, while varying the set of choice options and the constraint of choice. For the set of choice options, subjects were asked to choose for each food image in either a two-options condition (i.e., "take it" or "leave it"), or a three-options condition (i.e., "take it," "wait," or "leave it"). For the constraint of choice, subjects were instructed to select a maximum of either five items out of 80 (i.e., highly constrained) or 15 items out of 80 (i.e., less constrained). As in previous findings, the response times were consistently longer for "take it" than for "leave it" options. Importantly, this difference was exacerbated under high constraint, when subjects could select only five items, suggesting a role for opportunity-cost consideration in the decision process. Furthermore, as compared to two-options tasks, subjects consistently spent more time overall in the three-options tasks (with the option to defer), displaying lower acceptance rates, and particularly long response times for the "wait" option. This finding suggests that choice framing with a defer option nudges prolonged processing.