AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Practical Equivariances via Relational Conditional Neural Processes

Daolang Huang, Manuel Haussmann, Ulpu Remes, S. T. John, Grégoire Clarté, Kevin Sebastian Luck, Samuel Kaski, Luigi Acerbi

NeurIPS 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian decision-making under uncertainty

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
Replace CNP encoder with relational encoding (RCNP, stationary)CNP · Weakly-periodic GP d_x=1, OOIDscore: 2.88 -> 0.24Improved
Replace GNP with relational RGNP (stationary)GNP · Mixture d_x=5, OOIDlog-likelihood: -0.72 -> 0.04Improved
Replace CNP with RCNP (stationary)CNP · Mixture d_x=5, OOIDlog-likelihood: -1.71 -> -0.31Improved
Replace CNP with RGNP (stationary)CNP · Sawtooth d_x=5, OOIDlog-likelihood: -0.22 -> 1.13Improved
Use isotropic comparison (FullRCNP) instead of stationary (RCNP)RCNP · EQ GP isotropic d_x=5, OOIDscore: 0.45 -> 0.35Improved
Use isotropic comparison (FullRGNP) instead of stationary (RGNP)RGNP · EQ GP isotropic d_x=5, OOIDscore: 0.11 -> 0.25Hurt
Replace CNP with RCNP (stationary)CNP · EQ GP isotropic d_x=5, OOIDscore: 1.22 -> 0.45Improved
Use RGNP instead of ConvGNP on higher-dimensional tasksConvGNP · Weakly-periodic d_x=3, 5applicabilityImproved
Replace ConvGNP with RGNP (stationary)ConvGNP · Weakly-periodic GP d_x=1, OOIDscore: 0.01 -> 0.03No clear effect
Replace ConvGNP with RGNP (stationary)ConvGNP · Lotka-Volterra, forecasting, simulatednormalized log-likelihood: -4.30 -> -4.27Improved
Replace ConvGNP with RGNP (stationary)ConvGNP · Lotka-Volterra, interpolation, simulatednormalized log-likelihood: -3.46 -> -3.51Hurt
Replace CNP with RGNP (stationary)CNP · Reaction-Diffusion, completionnormalized log-likelihood: 0.13 -> 1.38Improved

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