AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

The Deep Weight Prior

Andrei Atanov, Arsenii Ashukha, Kirill Struminsky, Dmitriy Vetrov, Max Welling

ICLR 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Variational Bayesian deep learning · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a Deep Weight Prior learned from related-domain kernels instead of standard normal or log-uniform priorsBayesian CNN variational inference · MNIST and CIFAR-10 with limited training datatest accuracyImproved
Initialize fixed convolutional filters from the Deep Weight Prior instead of Xavier initializationCNN random feature extraction · MNIST and CIFAR-10test accuracyImproved
Initialize fixed convolutional filters with learned kernels instead of Xavier initializationCNN random feature extraction · MNIST and CIFAR-10test accuracyImproved
Replace Deep Weight Prior initialization with learned-filter initializationCNN random feature extraction · MNIST and CIFAR-10test accuracyMixed
Initialize convolutional layers from the Deep Weight Prior instead of Xavier initializationConvolutional VAE and CNN training · MNIST and CIFAR-10training speedImproved
Replace Deep Weight Prior initialization with learned-filter initializationConvolutional VAE and CNN training · MNIST and CIFAR-10training speedNo clear effect
Replace Deep Weight Prior with a learned multivariate Gaussian prior (ablation)Bayesian CNN variational inference · MNISTtest accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy