Copertina

The Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kravatskiy, Alexey, Kozyrev, Ivan, Kozlov, Nikolai, Vinogradov, Alexander, Merkulov, Daniil, Oseledets, Ivan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ImprovEvolve: Ask AlphaEvolve to Improve the Input Solution and Then Improvise
di: Kravatskiy, Alexey, et al.
Pubblicazione: (2026)

Another approach to build Lyapunov functions for the first order methods in the quadratic case
di: Merkulov, Daniil, et al.
Pubblicazione: (2023)

Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
di: Yukhimchuk, Alexander, et al.
Pubblicazione: (2026)

Decoupled Weight Decay for Any $p$ Norm
di: Outmezguine, Nadav Joseph, et al.
Pubblicazione: (2024)

Old Optimizer, New Norm: An Anthology
di: Bernstein, Jeremy, et al.
Pubblicazione: (2024)

PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
di: Lu, Yao, et al.
Pubblicazione: (2026)

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
di: Chezhegov, Savelii, et al.
Pubblicazione: (2024)

ARO: A New Lens On Matrix Optimization For Large Models
di: Gong, Wenbo, et al.
Pubblicazione: (2026)

Muon Optimizes Under Spectral Norm Constraints
di: Chen, Lizhang, et al.
Pubblicazione: (2025)

Black-Box Approximation and Optimization with Hierarchical Tucker Decomposition
di: Ryzhakov, Gleb, et al.
Pubblicazione: (2024)

DualSchool: How Reliable are LLMs for Optimization Education?
di: Klamkin, Michael, et al.
Pubblicazione: (2025)

Small Gradient Norm Regret for Online Convex Optimization
di: Gao, Wenzhi, et al.
Pubblicazione: (2026)

Self-Certifying Primal-Dual Optimization Proxies for Large-Scale Batch Economic Dispatch
di: Klamkin, Michael, et al.
Pubblicazione: (2025)

Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
di: Nguyen, Quan, et al.
Pubblicazione: (2024)

Hierarchical Mixture-of-Experts with Two-Stage Optimization
di: Molodtsov, Gleb, et al.
Pubblicazione: (2026)

Implicit Bias of AdamW: $\ell_\infty$ Norm Constrained Optimization
di: Xie, Shuo, et al.
Pubblicazione: (2024)

Stability of Primal-Dual Gradient Flow Dynamics for Multi-Block Convex Optimization Problems
di: Ozaslan, Ibrahim K., et al.
Pubblicazione: (2024)

$γ$-weakly $θ$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
di: Pedramfar, Mohammad, et al.
Pubblicazione: (2026)

Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise
di: Zhang, Jiayu, et al.
Pubblicazione: (2026)

From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem
di: Ameli, Mostafa, et al.
Pubblicazione: (2025)

Combining Reinforcement Learning and Optimal Transport for the Traveling Salesman Problem
di: Goh, Yong Liang, et al.
Pubblicazione: (2022)

On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer
di: Xu, Ruihan, et al.
Pubblicazione: (2026)

Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3
di: Rush, Keith
Pubblicazione: (2026)

Federated Majorize-Minimization: Beyond Parameter Aggregation
di: Dieuleveut, Aymeric, et al.
Pubblicazione: (2025)

Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
di: Riabinin, Artem, et al.
Pubblicazione: (2026)

Nonnegative Matrix Factorization in the Component-Wise L1 Norm for Sparse Data
di: Seraghiti, Giovanni, et al.
Pubblicazione: (2026)

DeMuon: A Decentralized Muon for Matrix Optimization over Graphs
di: He, Chuan, et al.
Pubblicazione: (2025)

Beyond Expectations: Learning with Stochastic Dominance Made Practical
di: Cen, Shicong, et al.
Pubblicazione: (2024)

Adaptive Primal-Dual Method for Safe Reinforcement Learning
di: Chen, Weiqin, et al.
Pubblicazione: (2024)

Exact Dual Geometry of SOC-ICNN Value Functions
di: Liu, Kang, et al.
Pubblicazione: (2026)

Primal-Dual Spectral Representation for Off-policy Evaluation
di: Hu, Yang, et al.
Pubblicazione: (2024)

Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers
di: Unser, Michael, et al.
Pubblicazione: (2025)

Training Deep Learning Models with Norm-Constrained LMOs
di: Pethick, Thomas, et al.
Pubblicazione: (2025)

Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
di: Kiyani, Elham, et al.
Pubblicazione: (2025)

The Newton-Muon Optimizer
di: Du, Zhehang, et al.
Pubblicazione: (2026)

Riemannian Bilevel Optimization
di: Dutta, Sanchayan, et al.
Pubblicazione: (2024)

Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less
di: Liu, Yuxing, et al.
Pubblicazione: (2026)

MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
di: Sharifnassab, Arsalan, et al.
Pubblicazione: (2024)

Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime
di: Wang, Yuqing, et al.
Pubblicazione: (2025)

From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto
di: Wasserkrug, Segev, et al.
Pubblicazione: (2024)