Estimating the expected output of wide random MLPs more efficiently than sampling
cs.LG, cond-mat.dis-nn, stat.ML
Submitted: 2026-05-06
Updated: 2026-11-02
Code: https://github.com/alignment-research-center/mlp_kprop
Terminology
Sources
- Formalizing the presumption of independence
- Wide Neural Networks as a Baseline for the Computational No-Coincidence Conjecture
- Gaussian Error Linear Units (GELUs)
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis