Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law Regimes
Yichen Wang, Fanghui Liu, Yudong Chen
Power-law learning curves are often treated as fixed properties of a model and its data, although learning-rate and batch-size schedules can change the observed loss. We study this…
cs.LG2026
Muon Sublates the Edge of Stability in LLM Pretraining
Yanzhe Chen, Qifang Zhao, Xiaoxiao Xu +1
Muon is increasingly used for language-model pretraining, yet its large-step dynamics are not captured by the classical edge-of-stability (EoS) picture of gradient descent (GD). In…
cs.LG2026
AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
Yuanhe Zhang, Jason D. Lee, Fanghui Liu
We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-end formal infrastructure implement the…