Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods

• URL: http://arxiv.org/abs/2510.10777v2
• Date: Wed, 22 Oct 2025 16:26:31 GMT
• Title: Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
• Authors: Andrey Veprikov, Arman Bolatov, Samuel Horváth, Aleksandr Beznosikov, Martin Takáč, Slavomir Hanzely,
• Abstract summary: We propose a unified framework generalizing descent, quasi-Newton methods, and adaptive methods through the novel notion of preconditioned matrix norms.<n>Within this framework, we provide the first systematic treatment of affine and scale invariance in the matrix- parameterized setting.<n>We introduce two new methods, $ttMuAdam$ and $texttMuAdam-SANIA$, which combine the spectral geometry of Muon with Adam-style preconditioning.
• Score: 50.070182958880146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry and leveraging curvature utilization. Steepest descent algorithms adapt to different geometries through norm choices but remain strictly first-order, whereas quasi-Newton and adaptive optimizers incorporate curvature information but are restricted to Frobenius geometry, limiting their applicability across diverse architectures. In this work, we propose a unified framework generalizing steepest descent, quasi-Newton methods, and adaptive methods through the novel notion of preconditioned matrix norms. This abstraction reveals that widely used optimizers such as SGD and Adam, as well as more advanced approaches like Muon and KL-Shampoo, and recent hybrids including SOAP and SPlus, all emerge as special cases of the same principle. Within this framework, we provide the first systematic treatment of affine and scale invariance in the matrix-parameterized setting, establishing necessary and sufficient conditions under generalized norms. Building on this foundation, we introduce two new methods, $\texttt{MuAdam}$ and $\texttt{MuAdam-SANIA}$, which combine the spectral geometry of Muon with Adam-style preconditioning. Our experiments demonstrate that these optimizers are competitive with, and in some cases outperform, existing state-of-the-art methods. Our code is available at https://github.com/brain-lab-research/LIB/tree/quasi_descent

Related papers

• Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness [51.302674884611335]
  This work introduces a hybrid non-Euclidean optimization method which generalizes norm clipping by combining steepest descent and conditional gradient approaches.<n>We discuss how to instantiate the algorithms for deep learning and demonstrate their properties on image classification and language modeling.
  arXiv  Detail & Related papers  (2025-06-02T17:34:29Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We propose a new family of algorithms that uses the linear minimization oracle (LMO) to adapt to the geometry of the problem.<n>We demonstrate significant speedups on nanoGPT training using our algorithm, Scion, without any reliance on Adam.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning [22.486361028522374]
  We show that layer-wise preconditioning methods are provably necessary from a statistical perspective.<n>We show that SGD is a suboptimal feature when extending beyond ideal isotropic inputs.<n>We show that standard tools like Adam preconditioning and batch-norm only mildly mitigate these issues.
  arXiv  Detail & Related papers  (2025-02-03T19:08:32Z)
• Mirror Descent Under Generalized Smoothness [23.5387392871236]
  We introduce a new $ell*$-smoothness concept that measures the norm of Hessians in terms of a general norm and its dual.<n>We establish convergence for mirror-descent-type algorithms, matching the rates under the classic smoothness.
  arXiv  Detail & Related papers  (2025-02-02T11:23:10Z)
• A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning [0.6526824510982802]
  Adaptive gradient methods have become popular in optimizing deep neural networks. Recent examples include AdaGrad and Adam. We develop a generic framework for adaptive gradient methods.
  arXiv  Detail & Related papers  (2022-06-04T17:55:33Z)
• Optimization on manifolds: A symplectic approach [127.54402681305629]
  We propose a dissipative extension of Dirac's theory of constrained Hamiltonian systems as a general framework for solving optimization problems. Our class of (accelerated) algorithms are not only simple and efficient but also applicable to a broad range of contexts.
  arXiv  Detail & Related papers  (2021-07-23T13:43:34Z)
• SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients [99.13839450032408]
  It is desired to design a universal framework for adaptive algorithms to solve general problems. In particular, our novel framework provides adaptive methods under non convergence support for setting.
  arXiv  Detail & Related papers  (2021-06-15T15:16:28Z)
• Leveraging Non-uniformity in First-order Non-convex Optimization [93.6817946818977]
  Non-uniform refinement of objective functions leads to emphNon-uniform Smoothness (NS) and emphNon-uniform Lojasiewicz inequality (NL) New definitions inspire new geometry-aware first-order methods that converge to global optimality faster than the classical $Omega (1/t2)$ lower bounds.
  arXiv  Detail & Related papers  (2021-05-13T04:23:07Z)
• Meta-Learning with Neural Tangent Kernels [58.06951624702086]
  We propose the first meta-learning paradigm in the Reproducing Kernel Hilbert Space (RKHS) induced by the meta-model's Neural Tangent Kernel (NTK) Within this paradigm, we introduce two meta-learning algorithms, which no longer need a sub-optimal iterative inner-loop adaptation as in the MAML framework. We achieve this goal by 1) replacing the adaptation with a fast-adaptive regularizer in the RKHS; and 2) solving the adaptation analytically based on the NTK theory.
  arXiv  Detail & Related papers  (2021-02-07T20:53:23Z)
• Adaptive extra-gradient methods for min-max optimization and games [35.02879452114223]
  We present a new family of minmax optimization algorithms that automatically exploit the geometry of the gradient data observed at earlier iterations. Thanks to this adaptation mechanism, the proposed method automatically detects whether the problem is smooth or not. It converges to an $varepsilon$-optimal solution within $mathcalO (1/varepsilon)$ iterations in smooth problems, and within $mathcalO (1/varepsilon)$ iterations in non-smooth ones.
  arXiv  Detail & Related papers  (2020-10-22T22:54:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.