Papers › Noisy Natural Gradient as Variational Inference

Noisy Natural Gradient as Variational Inference

6 Dec 2017ICML 2018 7arXiv:1712.02390archive 2025-07-28

Guodong Zhang, Shengyang Sun, David Duvenaud, Roger Grosse

Variational Bayesian neural nets combine the flexibility of deep learning with Bayesian uncertainty estimation. Unfortunately, there is a tradeoff between cheap but simple variational families (e.g.~fully factorized) or expensive and complicated inference procedures. We show that natural gradient ascent with adaptive weight noise implicitly fits a variational posterior to maximize the evidence lower bound (ELBO). This insight allows us to train full-covariance, fully factorized, or matrix-variate Gaussian variational posteriors using noisy versions of natural gradient, Adam, and K-FAC, respectively, making it possible to scale up to modern-size ConvNets. On standard regression benchmarks, our noisy K-FAC algorithm makes better predictions and matches Hamiltonian Monte Carlo's predictive variances better than existing methods. Its improved uncertainty estimates lead to more efficient exploration in active learning, and intrinsic motivation for reinforcement learning.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gd-zhang/noisy-K-FAC mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Active LearningEfficient ExplorationReinforcement LearningReinforcement Learning (RL)Variational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections