Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]

Provable convergence guarantees for black-box variational inference

Authors: Justin Domke, Robert Gower, Guillaume Garrigos

NeurIPS 2023 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We obtain non-asymptotic convergence guarantees for this problem, under simple assumptions. This provides rigorous guarantees that methods similar to those used in practice converge on realistic inference problems.
Researcher Affiliation Collaboration Justin Domke University of Massachusetts Amherst EMAIL, Guillaume Garrigos Université Paris Cité and Sorbonne Université, CNRS Laboratoire de Probabilités, Statistique et Modélisation F-75013 Paris, France EMAIL, Robert Gower Center for Computational Mathematics Flatiron Institute, New York EMAIL
Pseudocode Yes Algorithm 1 Prox-SGD with energy estimator and triangular factors, Algorithm 2 Proj-SGD with entropy estimator and symmetric factors, Algorithm 3 Proj-SGD with STL estimator and symmetric factors
Open Source Code No The paper does not contain any explicit statements about open-sourcing code or links to a code repository.
Open Datasets No This paper is theoretical and does not describe any experiments that would use datasets.
Dataset Splits No This paper is theoretical and does not describe any experiments that would specify data splits.
Hardware Specification No This paper is theoretical and does not describe any experimental setup or the hardware used.
Software Dependencies No This paper is theoretical and does not mention specific software dependencies with version numbers.
Experiment Setup No This paper is theoretical and does not describe any experimental setup or hyperparameters.