Effect of Synthetic Data Noise Scales on Cross-Domain Transfer Performance in Tabular Foundation Models

The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that encourage desirable model properties. Prior work has mainly focused on crafting high-quality priors over generators to improve overall pretraining performance. Our insight is that parameterizing the generator distribution enables an adversarial robustness perspective: during training, we can adapt the

Research goal: What is the effect of varying synthetic data noise scales on the cross-domain transfer performance of tabular foundation models evaluated using TabBench's domain adaptation metrics?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.1/10.