Variational Inference in high-dimensional linear regression

Authors: Sumit Mukherjee, Subhabrata Sen

JMLR 2022 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study high-dimensional bayesian linear regression with product priors. Using the nascent theory of non-linear large deviations (Chatterjee and Dembo, 2016), we derive sufficient conditions for the leading-order correctness of the naive mean-field approximation to the log-normalizing constant of the posterior distribution. Subsequently, assuming a true linear model for the observed data, we derive a limiting infinite dimensional variational formula for the log normalizing constant for the posterior. Furthermore, we establish that under an additional separation condition, the variational problem has a unique optimizer, and this optimizer governs the probabilistic properties of the posterior distribution. We provide intuitive sufficient conditions for the validity of this separation condition. Finally, we illustrate our results on concrete examples with specific design matrices.
Researcher Affiliation Academia Sumit Mukherjee EMAIL Department of Statistics Columbia University New York, NY 10027, USA; Subhabrata Sen EMAIL Department of Statistics Harvard University Cambridge, MA 02138, USA
Pseudocode No The paper describes theoretical methods and derivations but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing source code or links to code repositories for the methodology described.
Open Datasets No The paper discusses applications in genomics, finance, and public policy, but it does not use any specific publicly available datasets for empirical evaluation. It illustrates results on 'concrete examples with specific design matrices' which refer to theoretical models rather than actual public datasets.
Dataset Splits No The paper does not use specific datasets for empirical experiments, therefore, it does not discuss dataset splits for training, testing, or validation.
Hardware Specification No The paper focuses on theoretical derivations and does not describe any experimental setup or mention specific hardware used for computations.
Software Dependencies No The paper presents theoretical results and does not describe an implementation or list specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any empirical experiments or their setup, including hyperparameters or training configurations.