On Semi-parametric Inference for BART

Authors: Veronika Rockova

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we continue the theoretical investigation of BART initiated recently by (Roˇckov a and van der Pas, 2017). We focus on statistical inference questions. In particular, we study the Bernstein-von Mises (Bv M) phenomenon (i.e. asymptotic normality) for smooth linear functionals of the regression surface within the framework of nonparametric regression with fixed covariates. Our semi-parametric Bv M results show that, beyond rate-optimal estimation, BART can be also used for valid statistical inference.
Researcher Affiliation Academia 1Booth School of Business, University of Chicago. Correspondence to: Veronika Roˇckov a <Veronika.Rockova@Chicago Booth.edu>.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include any explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets No The paper describes a 'standard non-parametric regression setup' with 'fixed (rescaled) predictors' but does not mention the use of a specific, publicly available dataset (e.g., by name, citation, or link).
Dataset Splits No The paper is theoretical and focuses on statistical inference properties. It does not describe an experimental setup involving training, validation, and test dataset splits.
Hardware Specification No The paper is theoretical and does not describe any computational experiments that would require specific hardware. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not detail any software implementations or dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters, training configurations, or system-level settings.