arXiv AI
Jul 24
The Active Ingredient in Muon's Grokking
arXiv:2607. 20512v1 Announce Type: cross Abstract: The Muon optimizer reaches the grokking threshold on modular arithmetic faster than AdamW.
Muon Can Outperform Dedicated Continual Learning Methods
Related stories
arXiv Machine Learning
6d ago
Temperon: Full-Time SAM Quality at a Third Less Wall-Clock
The paper introduces Temperon, a training strategy that uses plain SGD for the first 43% of the epoch budget and then hands off to a SAM‑wrapped Muon refiner for the remaining training. On datasets such as CIFAR‑10/100, SVHN, and Tiny ImageNet, Temperon achieves the same or better accuracy as full‑time SAM while reaching key performance targets faster and at lower cost. Ablation studies show that the Muon refiner contributes the majority of the performance gain, while the initial SGD explorer and its restarts add negligible benefit.
arXiv Machine Learning
Aug 31
When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging
arXiv:2608.27518v1 Announce Type: new Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by c...
arXiv Machine Learning
Jun 3
MuLoCo: Muon is a practical inner optimizer for DiLoCo
arXiv:2505. 23725v3 Announce Type: replace Abstract: DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints.
arXiv AI
Jun 12
LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold
arXiv:2606. 12921v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) significantly reduces compute and memory costs for finetuning Deep Learning models but is often harder to tune than dense training: when using factor-wise optimizers such as AdamW, it is sensitive to initialization choices, its optimal learning rates transfer poorly across ranks, and it often fails to beat dense baselines.
arXiv AI
Aug 25
A Physical Response-and-Memory Model for Muon Optimization
The paper introduces a physical response-and-memory model for the Muon optimizer, explaining its semi‑orthogonalized momentum update as the maximally dissipative direction under an output‑side safety budget. It treats the weight matrix as a responsive medium with internal stress, showing that momentum corresponds to accumulated stress whose relaxation occurs over multiple timescales—fast and slow. Based on this, the authors propose the Bi‑Maxwell optimizer, which uses a two‑timescale memory kernel and achieves target loss in fewer steps on a public large‑language‑model benchmark.
arXiv Machine Learning
Jul 21
PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer
arXiv:2607. 17620v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) makes finetuning large language models cheaper by adding to each weight matrix a trainable low-rank update parameterized as the product of two matrices.
arXiv AI
Aug 10
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
arXiv:2608. 07436v1 Announce Type: new Abstract: Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head.
arXiv Machine Learning
Aug 20
LionMuon: Alternating Spectral and Sign Descent for Efficient Training
LionMuon is a new optimizer that alternates between Lion’s sign-based updates and Muon’s spectral matrix-sign updates on a fixed period P, sharing a single dual-EMA momentum buffer. This design keeps the memory footprint the same as Lion and half that of AdamW while reducing the average iteration cost compared to Muon. Experiments on 124M, 355M, and 720M models show LionMuon Pareto-dominates Muon, Lion, Signum, and AdamW across datasets and architectures, achieving lower validation loss with less compute.
arXiv AI
Jul 10
ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning
arXiv:2607. 07719v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task sequence LoRA-style methods keep stacking low-rank updates on the same frozen weight, so each new task tends to overwrite the previous ones.
arXiv AI
Jul 22
Soft-TransFormers for Continual Learning
arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.
arXiv Machine Learning
Jul 27
Hyperball May Not Be a Free Lunch
arXiv:2607. 22444v1 Announce Type: new Abstract: For scale-invariant deep networks, Hyperball-style optimizers have shown strong performance in large-scale training by fixing the norms of matrix-valued parameters and normalizing updates.