arXiv Machine Learning
OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 25
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors
arXiv:2606. 25971v1 Announce Type: new Abstract: Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object.
arXiv AI
Jun 4
Spectral Scaling Laws of Muon
arXiv:2606. 04058v1 Announce Type: cross Abstract: Orthonormalized update rules have rapidly become a leading choice of optimizer for training large language models, with recent open-source state-of-the-art models adopting Muon.
arXiv Machine Learning
Jul 28
The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning
arXiv:2607. 23711v1 Announce Type: new Abstract: LoRA fine-tuning can create intruder dimensions: new leading singular vectors of the updated weight matrix $W+BA$ that are nearly orthogonal to all pretrained singular vectors and that drive catastrophic forgetting.
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
Jun 30
Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks
arXiv:2606. 29176v1 Announce Type: new Abstract: A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation.
Hugging Face Trending Papers
Jun 28
Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks
A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation. Adam's per-coordinate preconditioner drifts along each symmetry orbit, which pulls the trajectory off the symmetry quotient where the optimization lives and blurs the singular-learning rate the quotient makes readable.