AI Paper Atlas

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

Efficient Approximate Inference for Stationary Kernel on Frequency Domain

Yohan Jung, Kyungwoo Song, Jinkyoo Park

ICML 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation

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
weighted sampling of spectral points (Ws) across mixture components (ablation)SVSS on Passenger SM kernel (Q=7, M=28) · Passengertest RMSE: RMSE 94.38 -> 54.00Improved
weighted sampling of spectral points (ablation)SVSS on CO2 (Q=10, M=40) · CO2test RMSE: RMSE 5.65 -> 4.34Improved
weighted sampling of spectral points (ablation)SVSS on Passenger (Q=10, M=40) · Passengertest RMSE: RMSE 50.56 -> 44.58Improved
weighted sampling of spectral points (ablation)SVSS on Passenger (Q=10, M=120) · Passengertest RMSE: RMSE 32.62 -> 33.56Hurt
approximate natural gradient in log domain (ablation)SVSS on bike dataset (Q=6) · Bike UCI ablationvalidation RMSE convergence / test RMSEImproved
reparameterization trick on sampled spectral points (ablation)SS (sparse spectrum optimization) on bike dataset · Bike UCI ablationiterations to converge (validation RMSE)Improved
KL regularization toward RBF spectral prior on spectral point distribution (ablation)SS+RP on bike dataset · Bike UCI ablationiterations to converge (validation RMSE)Improved
weighted sampling plus natural gradient (SVSS-WsNg) vs. SVSSSVSS on UCI regression datasets · UCI regression (sml, parkinsons, pol, kegg)test RMSE vs training timeImproved

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