AI Paper Atlas

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

Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics

Carles Domingo-Enrich, Youssef Mroueh

NeurIPS 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 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
Use feature-learning F1 discriminators instead of fixed-kernel F2 discriminatorsProbability metrics on constructed hypersphere distribution pairs · Hypersphere pairs μ_d, ν_d with high-frequency Legendre-harmonic differencesIPM: d_{B_F1}(μ_d,ν_d) / d_{B_F2}(μ_d,ν_d) = √N_{k,d}Improved
Use feature-learning F1 Stein discriminators instead of fixed-kernel F2 Stein discriminatorsStein discrepancy on constructed hypersphere distribution pairs · Hypersphere pairs μ_d, ν_d with high-frequency Legendre-harmonic differencesStein discrepancy: SD_{B_F1^d}(μ_d,ν_d) = 1Improved
Use feature-learning F1 rather than fixed-kernel F2Probability metrics comparing distributions that differ in one Gaussian variance · Gaussian distributions, varying dimensionsdiscrimination by IPM: F1 IPM is constant; F2 IPM decreasesImproved
Use max-sliced Wasserstein instead of sliced WassersteinGaussian distribution comparison · Gaussian distributions, varying dimensionsdiscrimination distance: max-sliced Wasserstein distance is constant; sliced Wasserstein distance decreasesImproved
Use feature-learning F1 rather than fixed-kernel F2 Stein discrepancyStein discrepancy estimates · Hypersphere pairs μ_d, ν_d with k=5ratio of F1 to F2 Stein discrepancies: empirical ratio is significantly above the theoretical lower boundImproved

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