AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features

Jiaolong Wang, Fode Zhang, Lingrui Wang

ICML 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Random feature approximation

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
inject fixed Spatial RFF (sigma=5) into the CNN discriminator (ablation)CNN GAN discriminator · CelebAFID: 240.47 -> 27.23Improved
enlarge Spatial-RFF bandwidth from sigma=1 to sigma=5 (ablation)CNN GAN discriminator · CelebAFID: 63.56 -> 30.07 -> 27.23 (sigma 1, 2, 5)Improved
enlarge Spatial-RFF bandwidth from sigma=1 to sigma=5 (ablation)CNN GAN discriminator · CelebASWD: 98.30 (sigma=1) -> 127.23 (sigma=2) -> 120.78 (sigma=5)Mixed
inject Spatial RFF to raise high-frequency capture (ablation)CNN GAN discriminator · CelebAHF energy (x10^-2): 24.89 -> 32.57Improved
use RFF linear critic instead of unconstrained MLP criticsAmari alpha-divergence estimator · synthetic truncated Gaussian vs uniform, d in {2,5,10}relative RMSEImproved
use RFF estimator instead of RKHS-regularized neural criticAmari alpha-divergence estimator · synthetic divergence estimationmean relative errorImproved

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