Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
Keywords: Bayesian experimental design, Bayesian adaptive design, optimal design, information maximization
TL;DR: Our semi-amortized Step-DAD approach improves adaptability, robustness and outperforms current state-of-the-art (fully amortized policy-based) design strategies
Abstract: We develop a semi-amortized, policy-based, approach to Bayesian experimental design (BED) called Step-wise Deep Adaptive Design (Step-DAD). Like existing, fully amortized, policy-based BED approaches, Step-DAD trains a design policy upfront before the experiment. However, rather than keeping this policy fixed, Step-DAD periodically updates it as data is gathered, refining it to the particular experimental instance. This allows it to improve both the adaptability and the robustness of the design strategy compared with existing approaches.
Primary Subject Area: Active learning, Data cleaning, acquisition for ML
Paper Type: Research paper: up to 8 pages
Participation Mode: In-person
Confirmation: I have read and agree with the workshop's policy on behalf of myself and my co-authors.
Submission Number: 65
Loading