How to scale your HEP ML models: A recipe for robust architecture comparisons at scale
hep-ex, cs.LG, hep-ph, physics.data-an
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/mvigl/scaling-laws-demo
Sources
- Scaling Laws for Neural Language Models
- Training Compute-Optimal Large Language Models
- GPT-4 Technical Report
- Scaling Vision Transformers
- Kimi K3: Open Frontier Intelligence
- Is Tokenization Needed for Masked Particle Modelling?
- EveNet: A Foundation Model for Particle Collision Data Analysis
- Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks
- Scaling Laws in Jet Classification
- Neural Scaling Laws for Boosted Jet Tagging
- Scaling Collider Event Generation with Residual-Quantized Tokens
- Scaling laws for amplitude surrogates
- FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics
- Towards Engineering Scaling Laws with Pretraining Data Composition
- Double Descent and Overparameterization in Particle Physics Data
- Resolving Discrepancies in Compute-Optimal Scaling of Language Models
- An Empirical Model of Large-Batch Training
- Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit
- Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining
- DeepSeek LLM: Scaling Open-Source Language Models with Longtermism