Oct 2025· arXiv.org· Vol abs/2510.13680· 3 citations· 48 references
Computer Science
TL;DR
The theoretical results show that GN's optimality for linear regression no longer holds under a poorly chosen basis under both population and stochastic updates, or a move from linear regression to a non-convex variant of logistic regression, and Adam-style methods offer genuine advantages over curvature-inspired preconditioning.
Abstract
Preconditioned methods are central to deep learning optimization. Predominant approaches include computationally light diagonal preconditioners such as Adam, which rely on gradient statistics, and second-order methods such as Gauss-Newton (GN), which capture richer curvature information. Seeking the best of both worlds, we disentangle the preconditioner design space into several factors, separating the choice of diagonal scaling (Adam-style versus GN-style) from 1) the basis choices under which the diagonal scaling operates, and 2) the gradient noises from mini-batching. Our theoretical results show that GN's optimality for linear regression no longer holds under a poorly chosen basis under both population and stochastic updates, or a move from linear regression to a non-convex variant of logistic regression. In these settings, Adam-style methods offer genuine advantages over curvature-inspired preconditioning, rather than serving merely as a tractable proxy. Empirical results on synthetic problems and CIFAR-10 support these findings.
Muon emerges as a strong competitor of the AdamW for LLM pretraining, because the matrix-wise update it employs can potentially incur smaller second-order penalty than the once dominating AdamW, which performs coordinate-wise update. However, the spectral flattening procedure in Muon is quite debatable since it discard...
Qiao-Zhe Zhang, Jun Sun, Ying-Zhuang Liu· 2 citations
An exact, information-theoretic analysis of stochastic gradient descent and its variants is given, showing that a preconditioned SGD step is the posterior-mean update of a Gaussian Bayes model, and that its one-step regret splits into an intrinsic-time cost and a change in comparator information.
Recent successes of matrix- and curvature-based optimizers have renewed interest in how update geometry shapes learning. These methods normalize or precondition updates, changing how different components progress during training. In deep matrix factorization, the geometry that slows gradient descent (GD) favors low-ran...
SoftServe, a family of QN methods designed to overcome non-convexity and enormous parameter sizes, is introduced, and derives positivedefinite curvature estimates from the variational objective of Berglund et al. (2025), even in the presence of negative curvature.
Joohwan Ko, Tetiana Parshakova, Diana Cai et al.· 0 citations
This work proposes a curvature-conditioned multiscale momentum method with sphere constraints, which significantly accelerates Muon across diverse architectures (dense, MoE) and model sizes (0.12B--2.3B parameters).
Shuchen Zhu, Yu-Xin Fang, Mingze Wang et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026