AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Variational Inference for Infinitely Deep Neural Networks

Achille Nazaret, David Blei

ICML 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Variational methods for sequence models · 1 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 posterior over truncation depths and combine predictions across those depthsUDN with fully connected networks · Spiral classification D(ω), test accuracy averaged over ωaccuracy (%): 90.5 -> 91.7Improved
Use a posterior over truncation depths and combine predictions across those depthsUDN with ResNet · CIFAR-10 testaccuracy: 94.0 -> 94.4Improved
Increase spiral rotation complexityUDN posterior · Spiral classification D(ω)posterior truncation depthMixed
Use a harder class pair (cat vs dog) instead of an easier pair (deer vs car)UDN posterior · CIFAR-10 two-class subsamplesposterior truncation depthImproved
Use the full CIFAR-10 task instead of the two-class subsamplesUDN posterior · CIFAR-10posterior truncation depthImproved
Combine predictions from multiple depths rather than use an individual finite-depth networkDUN-10 · Spiral classification D(ω), test accuracy averaged over ωaccuracy (%): 89.3 -> 90.5Improved

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