Representing MAX functions using two-hidden-layer ReLU networks

arXiv:2608.25221 · cs.LG, math.OC, stat.ML · Submitted 2026-08-25 · Read on arXiv

cs.LG, math.OC, stat.ML

Submitted: 2026-08-25

Updated: 2026-08-25

Terminology

• Activation Function — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes

Sources

• On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth
• Shallower ReLU Network Representations via Exact Linear Algebra

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks