LassoFlexNet: a Flexible Neural Architecture for Tabular Data

Despite their dominance in vision and language, deep neural networks often underperform relative to tree-based models on tabular data. To bridge this gap, we incorporate five key inductive biases into deep tabular learning: robustness to irrelevant features, axis alignment, localized irregularities, feature heterogeneity, and training stability. We propose LassoFlexNet, an architecture that evaluates the linear and nonlinear marginal contribution of each input via Per-Feature Embeddings, and sparsely selects relevant variables using a Tied Group Lasso mechanism. Because these components introduce optimization challenges that destabilize standard proximal methods, we analyze stochastic hierarchical proximal dynamics and develop a Sequential Hierarchical Proximal Adaptive Gradient optimizer with exponential moving averages (EMA) designed to stabilize training in practice. Across 52 datasets from three benchmarks, LassoFlexNet matches or outperforms leading tree-based models, achieving up to a $10$% relative gain, while maintaining Lasso-like interpretability. We substantiate these empirical results with ablation studies and theoretical proofs confirming the architecture's enhanced expressivity and structural breaking of undesired rotational invariance.