Do ResNets Route? Sparse Interaction Experts in Residual Networks
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- Shapley Value as Principled Metric for Structured Network Pruning
- HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
- Path-Constrained Mixture-of-Experts
- GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- The Loss Surface of Residual Networks: Ensembles and the Role of Batch Normalization
- Learning Identity Mappings with Residual Gates
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Highway Networks
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