Convergence Rates of Variational Inference in Sparse Deep Learning

Authors: Badr-Eddine Chérief-Abdellatif

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we show that variational inference for sparse deep learning retains precisely the same generalization properties than exact Bayesian inference. In particular, we show that a wise choice of the neural network architecture leads to near-minimax rates of convergence for Hölder smooth functions. Additionally, we show that the model selection framework over the architecture of the network via ELBO maximization does not overfit and adaptively achieves the optimal rate of convergence.
Researcher Affiliation Academia CREST ENSAE Institut Polytechnique de Paris. Correspondence to: Badr-Eddine Chérief-Abdellatif <badr.eddine.cherief.abdellatif@ensae.fr>
Pseudocode No The paper describes methods and theoretical analyses but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not mention providing open-source code for the methodology described.
Open Datasets No The paper describes a theoretical nonparametric regression framework using a collection of random variables, but it does not use or provide access information for a specific, publicly available dataset.
Dataset Splits No The paper is purely theoretical and does not describe empirical experiments with data splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not report on computational experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe specific software implementations with version numbers.
Experiment Setup No The paper is purely theoretical and does not describe an experimental setup with specific hyperparameters or system-level training settings.