Skip to content
conftrace_

compute-optimal training

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model scaling (2) bert-style model (1) data-to-model ratio (1) neural scaling law (1) scaling collapse (1) sgd noise dynamics (1) supercollapse (1) transformer model (1) large language model (1) glue benchmark (1)

Papers

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks ICML 2025 Training compute-optimal transformer encoder models EMNLP 2025 An empirical analysis of compute-optimal large language model training NeurIPS 2022