Closed-Form Last Layer Optimization
cs.LG, stat.ML
Submitted: 2025-10-06
Updated: 2026-11-06
Code: https://github.com/deepmind/dsprites-dataset
Terminology
Sources
- Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
- Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
- Large Batch Training of Convolutional Networks
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