Automating the practice of science: Opportunities, challenges, and implications

S Musslick, LK Bartlett, SH Chandramouli… - Proceedings of the …, 2025 - pnas.org
Automation transformed various aspects of our human civilization, revolutionizing industries
and streamlining processes. In the domain of scientific inquiry, automated approaches …

The Fundamental Dilemma of Bayesian Active Meta-learning

SJ Sloman, A Bharti, S Kaski - arXiv preprint arXiv:2310.14968, 2023 - arxiv.org
Many applications involve estimation of parameters that generalize across multiple diverse,
but related, data-scarce task environments. Bayesian active meta-learning, a form of …

Bayesian Active Learning in the Presence of Nuisance Parameters

SJ Sloman, A Bharti, J Martinelli, S Kaski - 2023 - research.manchester.ac.uk
In many settings, such as scientific inference, optimization, and transfer learning, the learner
has a well-defined objective, which can be treated as estimation of a target parameter, and …

Parametric Prospect Theory: Experimental Design, Certainty E⁄ Ects and Complexity Bias

I Fraser, KG Balcombe - Certainty E⁄ Ects and Complexity Bias, 2023 - papers.ssrn.com
We introduce an alternative approach to experimental design aimed at collecting data for
parametric estimation of the cumulative form of Prospect Theory (PT). Our approach …

A Note on an Alternative Approach to Experimental Design of Lottery Prospects

K Balcombe, I Fraser - 2024 - mpra.ub.uni-muenchen.de
e introduce an alternative approach to lottery prospects experimental design aimed at
collecting experimental data for parametric estimation of the cumulative form of Prospect …

Bayesian Active Meta-Learning under Prior Misspecification

SJ Sloman, A Bharti, S Kaski - openreview.net
We study a setting in which an active meta-learner aims to separate the idiosyncracies of a
particular task environment from information that will transfer between task environments. In …