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

High-Dimensional Conditional Independence Testing via Random Projection Aggregation

NeurIPS 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel two-sample testing

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes RP-CIT, a conditional independence test that aggregates statistics over random one-dimensional projections of X and Y to remain effective in high dimensions.

Problem

Nonparametric conditional independence testing degrades in high dimensions because nonparametric estimation suffers from the curse of dimensionality.

Approach

Project X and Y onto random one-dimensional directions and aggregate the resulting CI statistics, so that the test avoids high-dimensional nonparametric estimation.

Closest papers by meaning

• Randomized tests for high-dimensional regression: A more efficient and powerful solution (NeurIPS 2020 · similarity 0.90)
• Conditional Diffusion Models Based Conditional Independence Testing (AAAI 2025 · similarity 0.85)
• A Sample Efficient Conditional Independence Test in the Presence of Discretization (ICML 2025 · similarity 0.85)
• On the Hardness of Conditional Independence Testing In Practice (NeurIPS 2025 · similarity 0.84)
• A Conditional Independence Test in the Presence of Discretization (ICLR 2025 · similarity 0.84)
• On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery (ICML 2024 · similarity 0.83)