Fast Treatment Personalization with Latent Bandits in Fixed-Confidence Pure Exploration

Authors: Newton Mwai Kinyanjui, Emil Carlsson, Fredrik D. Johansson

TMLR 2023 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we present results from an experimental study based on realistic simulation data for Alzheimer s disease, demonstrating that our formulation and algorithms lead to a significantly reduced stopping time.
Researcher Affiliation Academia Newton Mwai EMAIL Department of Computer Science and Engineering Chalmers University of Technology Emil Carlsson EMAIL Department of Computer Science and Engineering Chalmers University of Technology Fredrik D. Johansson EMAIL Department of Computer Science and Engineering Chalmers University of Technology
Pseudocode Yes Algorithm 1 LLPT Explorer and Divergence Explorer
Open Source Code No The paper does not provide an explicit statement about releasing code or a link to a code repository for the described methodology.
Open Datasets Yes As treatment personalization task, we use the Alzheimer s Disease Causal estimation Benchmark (ADCB) environment (Kinyanjui and Johansson, 2022).
Dataset Splits No The paper describes experiments using a simulator where "A new patient is sampled from the environment". It does not provide specific training/validation/test dataset splits in terms of percentages, sample counts, or explicit splitting methodology for a static dataset.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments (e.g., GPU models, CPU types, or memory specifications).
Software Dependencies No The paper does not provide specific software names with version numbers (e.g., Python, PyTorch, or specific solvers with versions) that would be needed to replicate the experiment.
Experiment Setup Yes Evaluation metrics We compare empirical estimates of the expected stopping time E[ ], convergence of the posterior probability p(ˆst | ht) with t, and the average correctness level, E[1[ˆa = aú]], of the different algorithms for i) different levels of confidence œ (0, 1/2) under a fixed noise level > 0 and ii) different levels of noise for a fixed .