Nowcasting Future Performance for Population Pruning in Survival-of-the-Fittest Training
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/RicoStaedeli/sotf-training
Terminology
Sources
- Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
- Population Based Training of Neural Networks
- A Survey of Weight Space Learning: Understanding, Representation, and Generation
- Predicting Neural Network Accuracy from Weights
- Accelerating Training with Neuron Interaction and Nowcasting Networks
- Towards Scalable and Versatile Weight Space Learning
- An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability
- Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy
- A Model Zoo on Phase Transitions in Neural Networks
- Model Zoos: A Dataset of Diverse Populations of Neural Network Models
- A Model Zoo of Vision Transformers
- WeightCLIP: Aligning Datasets and Models for Weight Space Learning
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