Work

Good Initializations of Variational Bayes for Deep Models

Year: 2018

Type: conference-paper

Abstract: Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational inference. We address this by proposing a novel layer-wise initialization strategy based on Bayesian linear models. The proposed method is extensively validated on regression and classification tasks, including Bayesian DeepNets and ConvNets, showing faster and better convergence compared to alternatives inspired by the literature on initializations for loss minimization.

Source: Graduate School and Research Center in Digital Science (EURECOM)

DOI: 10.48550/arxiv.1810.08083

Authors: Rossi, Simone, Michiardi, Pietro, Filippone, Maurizio

Institution: EURECOM

Language: English

Topic: Gaussian Processes and Bayesian Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2896485554

FWCI: 0.712

Cites:

Cited by: 13

Related to: 20