On Minimal Depth in Neural Networks

arXiv:2402.15315 · cs.LG, cs.DM, math.CO · Submitted 2024-02-23 · Read on arXiv

cs.LG, cs.DM, math.CO

Submitted: 2024-02-23

Updated: 2026-09-22

Comments: 19 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Neural Network Approximation — 2× in this paper · explained in 2 episodes
• APEX — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes

Sources

• On the Depth of Monotone ReLU Neural Networks and ICNNs
• Better Neural Network Expressivity: Subdividing the Simplex
• Depth-Bounds for Neural Networks via the Braid Arrangement
• A new Input Convex Neural Network with application to options pricing
• Lower bounds over Boolean inputs for deep neural networks with ReLU gates

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