AI Paper Atlas

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

Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space

Sandesh Ghimire, Aria Masoomi, Jennifer Dy

NeurIPS 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Annealing and divergence-based variational objectives · 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 an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorKL estimation · 2D Gaussian KL (true KL 1.3)estimation error: 0.5 to 0.04Improved
Use an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorKL estimation · 2D Gaussian KL (true KL 1.3)variance: 0.2 to 0.002Improved
Use an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorKL estimation · 2D Gaussian KL (true KL 13.8)estimation error: 5.8 to 1.07Improved
Use an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorKL estimation · 2D Gaussian KL (true KL 13.8)variance: 223 to 4.4Improved
Use an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorKL estimation · 2D Gaussian KL (true KL 38.29)estimation error: 60.6 to 9.7Improved
Use an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorKL estimation · 2D Gaussian KL (true KL 38.29)variance: 3521 to 33Improved
Increase RKHS norm regularization (ablation)RKHS discriminator · 2D Gaussian KL estimationvarianceImproved
Increase RKHS norm regularization (ablation)RKHS discriminator · 2D Gaussian KL estimationbiasMixed
Use an RKHS discriminator with complexity control instead of the basic neural-network discriminatorAdversarial Variational Bayes · MNISTtraining stabilityImproved
Use an RKHS discriminator with complexity control instead of an unconstrained neural network discriminatorMutual information estimation · 20-d Gaussian distributions; mutual information from 2 to 10mutual information estimation performanceMixed
Increase RKHS norm regularization (ablation)RKHS discriminator · Mutual information estimation on 20-d Gaussian distributionsvarianceImproved
Increase RKHS norm regularization (ablation)RKHS discriminator · Mutual information estimation on 20-d Gaussian distributionsbiasHurt

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