AI Paper Atlas

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

Representation Learning for Equivariant Inference with Guarantees

Daniel Ordonez-Apraez, Vladimir R Kostic, Alek Fröhlich, Vivien Brandt, Karim Lounici, Massimiliano Pontil

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 0 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
add G-equivariance (eNCP) to NCP for uncertainty quantificationNCP · Quadruped locomotion UQ (90% target)Coverage: 56.9 -> 95.0Improved
add equivariance (eNCP) vs symmetry-agnostic NCP for relaxed coverageNCP · Quadruped locomotion UQ (90% target)r-Coverage: 99.5 -> 99.5No clear effect
add equivariance to CQR (eCQR)CQR · Quadruped locomotion UQ (90% target)Coverage: 8.5 -> 6.7No clear effect
add equivariance to CQR (eCQR) for set sizeCQR · Quadruped locomotion UQ (90% target)Set-size: 1.4×10^8 -> 1.7×10^7Improved
add equivariance (eNCP) to NCP for set sizeNCP · Quadruped locomotion UQ (90% target)Set-size: 2.6×10^10 -> 4.3×10^9Improved

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