Cover Image

Muon is Not That Special: Random or Inverted Spectra Work Just as Well

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shumaylov, Zakhar, Da Costa, Nathaël, Zaika, Peter, Mucsányi, Bálint, Massucco, Alex, Gelberg, Yoav, Schönlieb, Carola-Bibiane, Gal, Yarin, Hennig, Philipp
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Numerical Analysis Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Data-driven approaches to inverse problems
by: Schönlieb, Carola-Bibiane, et al.
Published: (2025)

Rethinking Approximate Gaussian Inference in Classification
by: Mucsányi, Bálint, et al.
Published: (2025)

Geometric Gaussian Approximations of Probability Distributions
by: Da Costa, Nathaël, et al.
Published: (2025)

When is a System Discoverable from Data? Discovery Requires Chaos
by: Shumaylov, Zakhar, et al.
Published: (2025)

Generalized Lie Symmetries in Physics-Informed Neural Operators
by: Wang, Amy Xiang, et al.
Published: (2025)

Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
by: Shumaylov, Zakhar, et al.
Published: (2024)

Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
by: Shumaylov, Zakhar, et al.
Published: (2024)

Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
by: Diepeveen, Willem, et al.
Published: (2024)

Hamiltonian Matching for Symplectic Neural Integrators
by: Canizares, Priscilla, et al.
Published: (2024)

Symplectic Neural Flows for Modeling and Discovery
by: Canizares, Priscilla, et al.
Published: (2024)

Deep Network Trainability via Persistent Subspace Orthogonality
by: Massucco, Alex, et al.
Published: (2025)

Diffeomorphism-Equivariant Neural Networks
by: Oettinger, Josephine Elisabeth, et al.
Published: (2026)

Training Transformers for KV Cache Compressibility
by: Gelberg, Yoav, et al.
Published: (2026)

Debiasing Mini-Batch Quadratics for Applications in Deep Learning
by: Tatzel, Lukas, et al.
Published: (2024)

The Curse of Recursion: Training on Generated Data Makes Models Forget
by: Shumailov, Ilia, et al.
Published: (2023)

Adaptive Coordinate Transforms for Neural Operators
by: Liu, Chaoyu, et al.
Published: (2026)

Benchmarking learned algorithms for computed tomography image reconstruction tasks
by: Kiss, Maximilian B., et al.
Published: (2024)

Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
by: Massucco, Alex, et al.
Published: (2026)

Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
by: Mucsányi, Bálint, et al.
Published: (2024)

SpectraKAN: Conditioning Spectral Operators
by: Cheng, Chun-Wun, et al.
Published: (2026)

Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective
by: Iske, Meira, et al.
Published: (2026)

Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks
by: Gelberg, Yoav, et al.
Published: (2024)

Sample Path Regularity of Gaussian Processes from the Covariance Kernel
by: Da Costa, Nathaël, et al.
Published: (2023)

Iterative Deployment Improves Planning Skills in LLMs
by: Corrêa, Augusto B., et al.
Published: (2025)

Boosting Data-Driven Mirror Descent with Randomization, Equivariance, and Acceleration
by: Tan, Hong Ye, et al.
Published: (2023)

On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization
by: Shumaylov, Zakhar, et al.
Published: (2025)

Spatiotemporal Graph Neural Network Modelling Perfusion MRI
by: Yan, Ruodan, et al.
Published: (2024)

Inverse Evolution Data Augmentation for Neural PDE Solvers
by: Liu, Chaoyu, et al.
Published: (2025)

Potential Contrast: Properties, Equivalences, and Generalization to Multiple Classes
by: Peaslee, Wallace, et al.
Published: (2025)

Generative Unordered Flow for Set-Structured Data Generation
by: Li, Yangming, et al.
Published: (2025)

Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling
by: Khelifa, Naïl, et al.
Published: (2025)

Stochastic Primal-Dual Three Operator Splitting Algorithm with Extension to Equivariant Regularization-by-Denoising
by: Tang, Junqi, et al.
Published: (2022)

Continuous Learned Primal Dual
by: Runkel, Christina, et al.
Published: (2024)

TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
by: Eliasof, Moshe, et al.
Published: (2025)

Approximation Theory for Lipschitz Continuous Transformers
by: Furuya, Takashi, et al.
Published: (2026)

Approximation theory for 1-Lipschitz ResNets
by: Murari, Davide, et al.
Published: (2025)

On the Effectiveness of Random Weights in Graph Neural Networks
by: Bui, Thu, et al.
Published: (2025)

laplax -- Laplace Approximations with JAX
by: Weber, Tobias, et al.
Published: (2025)

Stochastic Multiresolution Image Sketching for Inverse Imaging Problems
by: Perelli, Alessandro, et al.
Published: (2024)

Proximal Langevin Sampling With Inexact Proximal Mapping
by: Ehrhardt, Matthias J., et al.
Published: (2023)