Rethinking Neural Nonlinearity as Gating

arXiv:2607.03148 · cs.LG, cs.AI, cs.AR · Submitted 2026-07-03 · Read on arXiv

cs.LG, cs.AI, cs.AR

Submitted: 2026-07-03

Updated: 2026-07-03

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

Terminology

• Threshold Gating — 3× in this paper
• Activation Function — 1× in this paper · explained in 1 episode
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Learning Activation Functions to Improve Deep Neural Networks
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Gaussian Error Linear Units (GELUs)
• Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
• Mish: A Self Regularized Non-Monotonic Activation Function
• GLU Variants Improve Transformer

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks