Kernel Variable Importance Measure (KvIM) Paper and Supporting Data

Bingyao Huang's 2026 paper introduces a novel kernel variable importance measure (KvIM) based on maximum mean discrepancy. The associated dataset, available on figshare, includes files for the paper and likely supporting numerical experiments. The resource is licensed under CC-BY-4.0.

Use Cases

• Evaluating feature importance in high-dimensional datasets based on the described kernel-based method.
• Benchmarking the proposed KvIM against other variable importance measures using the provided numerical experiments.
• Applying the KvIM-enhanced classification approach to classification problems as described in the paper.
• Implementing the online KvIM for analysis of streaming datasets as proposed by the author.

Strengths

• Dataset is associated with a peer-reviewed paper describing a novel, nonparametric variable importance measure.
• Files are available in multiple formats (PDF, ZIP) totaling 2.2 MB.

Limitations

• Row count and column-level documentation are absent; data structure must be inferred after download.
• The description focuses on the methodological paper; the exact content and format of the supporting data files are unspecified.

Provenance

Source

Bingyao Huang via figshare.

Collection Method

Likely generated for numerical experiments supporting the academic paper.

Time Range

null

Freshness

Last updated 2026-04 09 21:06:53.

Geography

null