Every Layer Counts: An Exponential L 2 Depth Hierarchy for ReLU Networks

arXiv:2608.23877 · cs.LG · Submitted 2026-08-24 · Read on arXiv

cs.LG

Submitted: 2026-08-24

Updated: 2026-08-30

Terminology

• Accuracy — 13× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• On the Depth of Monotone ReLU Neural Networks and ICNNs
• Most ReLU Networks Admit Identifiable Parameters
• Depth Lower Bounds for ReLU Networks with Binary Inputs
• Lower bounds over Boolean inputs for deep neural networks with ReLU gates
• Shallower ReLU Network Representations via Exact Linear Algebra
• Depth Separations in Neural Networks: What is Actually Being Separated?

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