arXiv:2505. 24275v4 Announce Type: replace Abstract: We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2606. 17526v1 Announce Type: new Abstract: Efficient optimization is essential for training large language models.
The paper introduces two variance‑adaptive variants of the Muon optimizer—Muon‑NSR and Muon‑VS—for language model pretraining. Both methods incorporate gradient‑variance information into Muon’s orthogonalization process without adding extra hyperparameters, preserving its spectral normalization structure. Experiments on Llama‑style and GPT‑2 models ranging from 125 M to 1.2 B parameters show that these variants outperform well‑tuned Muon baselines and achieve up to a 1.33× step‑to‑target speedup on Llama‑1.2B.
arXiv:2606. 13894v1 Announce Type: cross Abstract: AdamW is a default optimizer for modern deep learning, but its first and second moment states add roughly two parameter-sized buffers to training memory.
arXiv:2608. 08961v1 Announce Type: new Abstract: AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware.
MONA is a new optimizer that extends the Muon optimizer by adding a Nesterov‑style acceleration term derived from an exponential moving average of gradient differences. The paper provides a convergence analysis showing that this term offers curvature‑aware corrections while maintaining Muon’s spectral‑norm regularization. Empirical results demonstrate that MONA outperforms both Muon and AdamW on Mixture‑of‑Experts pretraining across models ranging from 1 B to 68 B parameters, and achieves state‑of‑the‑art performance on downstream benchmarks after fine‑tuning the largest model.
AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware. We benchmark five gradient optimizers (SGD, Adam, Adagrad, Adadelta, and Conjugate Gradient Descent) under three memory strategies (standard training, gradient checkpointing, and gradient accumulation) across four transformer architectures (ViT, ModernBERT, Llama 3.