Comparative Analysis of Evaluation Metrics for Generative Models on Large-Scale Tabular Datasets and Novel Proposals for

Generative models have revolutionized multiple domains, yet their application to tabular data remains underexplored. Evaluating generative models for tabular data presents unique challenges due to structural complexity, large-scale variability, and mixed data types, making it difficult to intuitively capture intricate patterns. Existing evaluation metrics offer only partial insights, lacking a comprehensive measure of generative performance. To address this limitation, we propose three novel evaluation metrics: FAED, FPCAD, and RFIS. Our extensive experimental analysis, conducted on three stan

Research goal: How do existing evaluation metrics for generative models compare in measuring performance on large-scale tabular datasets with varying distributions, and what novel metrics could better capture robustness and generalization across domains?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.