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:2609.24678v1 Announce Type: new Abstract: Continual learning with Low-Rank Adapters (LoRA) typically mitigates forgetting by penalizing the overlap between a new update and the accumulated past...
arXiv:2504. 15610v4 Announce Type: replace Abstract: Fine-tuning a 7B language model for specialized advising is attractive in resource-constrained settings, but multi-epoch runs routinely exceed the wall-clock limits of the free-tier GPUs (Kaggle, Colab) such users rely on.
arXiv:2609.13922v1 Announce Type: new Abstract: Minibatch persistency reuses data instead of reading it: rather than drawing a fresh minibatch at every optimizer step, it takes K consecutive steps on...
arXiv:2608. 13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU.
arXiv:2608.21098v1 Announce Type: new Abstract: Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or har...
arXiv:2606. 29119v1 Announce Type: cross Abstract: We introduce a pre-registered screening rule that decides, before any implementation, whether an evolutionary / population / lifecycle outer loop over neural-network parameters or structure is worth building.
arXiv:2603. 28921v3 Announce Type: replace-cross Abstract: The critical damping condition of the damped harmonic oscillator model of SGD with momentum (Qian, 1999) yields a momentum schedule with no tuned hyperparameters: mu(t) = 1 - 2*sqrt(alpha(t)).
arXiv:2607. 21535v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel.
A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We s...
The paper introduces Stiefel Attention, which constrains the query and key projection matrices of transformers to the Stiefel manifold and optimizes them with a Riemannian Adam variant. It demonstrates that this approach yields steepest‑descent updates, is well‑conditioned, and preserves learned attention geometry during weight decay. Empirical results show significant accuracy gains on modular arithmetic grokking and CIFAR‑10 patches, with the improvement attributed to a step‑scale‑free update rule rather than equivariance or projector changes.
arXiv:2606. 11387v1 Announce Type: cross Abstract: Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets.
arXiv:2607. 19058v1 Announce Type: cross Abstract: Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training: on a 6.