The paper proposes constraining the query and key projection matrices in Transformer attention to the Stiefel manifold and optimizing them with a Riemannian Adam optimizer. It demonstrates that this geometric constraint yields significant performance gains on a CIFAR‑10 patch benchmark, with the constrained model outperforming standard AdamW by up to +6.79 percentage points. The authors also show that weight decay has no effect on the constrained frames and that the improvement is driven by a scale‑free step size rather than the manifold projection or equivariance properties.
By Rub\'en Dar\'io Guerrero
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.
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.
By Tejas Pradeep Shirodkar
arXiv:2608. 07436v1 Announce Type: new Abstract: Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head.
By Ali Janati, Kaoutar El Maghraoui, Andrei Kanavalau, Anass Belfatmi
arXiv:2607. 03998v1 Announce Type: new Abstract: The local sharpness of the loss, the top Hessian eigenvalue $\lambda_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or Hessian-vector iterations.
By Ashmitha R, J\"org Frochte
arXiv:2606. 03003v1 Announce Type: cross Abstract: A latent world model built from an equivariant encoder $E$ and an equivariant predictor $f$ inherits a provable symmetry of its training loss: when the world's dynamics genuinely carries a group $G$ acting on latents by an orthogonal representation $\rho(g)$, the one-step prediction relMSE is exactly invariant across the whole group, so fitting the dynamics on a restricted slice of orientations mathematically determines it on the entire orbit (j\v{u} y\=i f\v{a}n s\=an).
By Hongbo Wang (Stony Brook University)
arXiv:2608. 14803v1 Announce Type: new Abstract: A recent line of work recasts the post-memorization phase of grokking as constrained optimization: once a network interpolates the training set, weight decay drives a slow drift along the zero-loss manifold toward lower norm.
By Suvinava Basak
arXiv:2608. 05136v1 Announce Type: new Abstract: Gradient descent on a factored model $W = UV^\top$ is implicitly biased toward low-rank solutions, while Adam, starting from the same small initialization, is not.
By Devender Singh
The paper introduces Activation-Keyed Momentum (AK‑Momentum), a momentum update that uses the input activation of a linear layer as a key to apply a delta‑rule update, allowing each direction to decay at a rate proportional to its frequency of appearance. AK‑Momentum is proven to be a valid momentum, incorporates input‑side curvature correction without matrix inversion, and clears stale directions faster than traditional exponential moving average (EMA) under both fixed and drifting optima. It can replace the momentum buffer of any optimizer, scales with width under μP, adds only 22–25% extra compute, and demonstrates significant step‑count reductions in FineWeb‑Edu pretraining and other benchmarks.
whyItMatters":"AK‑Momentum offers a principled, efficient way to adapt momentum decay to anisotropic training dynamics, improving convergence speed and stability across a range of models and datasets."
By Euijin Hong, Guannan Qu
ExGrad introduces explicit clean‑gradient subtraction in adversarial training by constructing clean‑input, adversarial‑input, and adversarial‑weight‑perturbed gradients and solving a globally solvable three‑variable problem to select coefficients. Across CIFAR‑10, CIFAR‑100, and ImageNet‑100, ExGrad consistently outperforms AWP and PGD‑AT, with the strongest gains at larger affine radii. The method demonstrates that negative clean coefficients, when properly tuned, improve robust accuracy without sacrificing clean performance.
By Zhiyuan Ye, Xiangyu Zhou, Ji Qi, Hao Zhang, Yi Zhou
arXiv:2607. 20512v1 Announce Type: cross Abstract: The Muon optimizer reaches the grokking threshold on modular arithmetic faster than AdamW.
By Yufeng Wang
arXiv:2608. 19491v1 Announce Type: new Abstract: Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate.
By Euijin Hong, Guannan Qu