Cover Image

Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bright-Thonney, Samuel, Harvey, Thomas R., Lukas, Andre, Thaler, Jesse
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence High Energy Physics - Theory Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Safe but Incalculable: Energy-weighting is not all you need
by: Bright-Thonney, Samuel, et al.
Published: (2023)

Covariant Gradient Descent
by: Guskov, Dmitry, et al.
Published: (2025)

Natural Gradient Descent for Control
by: Esmzad, Ramin, et al.
Published: (2025)

Tropical Gradient Descent
by: Talbut, Roan, et al.
Published: (2024)

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
by: Yang, Tong, et al.
Published: (2025)

SPECTER: Efficient Evaluation of the Spectral EMD
by: Gambhir, Rikab, et al.
Published: (2024)

An Improved Last-Iterate Convergence Rate for Anchored Gradient Descent Ascent
by: Surina, Anja, et al.
Published: (2026)

Gradient Descent Efficiency Index
by: Dhingra, Aviral
Published: (2024)

Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion
by: Cai, HanQin, et al.
Published: (2022)

Flavor Patterns of Fundamental Particles from Quantum Entanglement?
by: Thaler, Jesse, et al.
Published: (2024)

Thermal Bootstrap of Matrix Quantum Mechanics
by: Cho, Minjae, et al.
Published: (2024)

Copositive geometry of Feynman integrals
by: Sturmfels, Bernd, et al.
Published: (2025)

Bootstrapping Nonequilibrium Stochastic Processes
by: Cho, Minjae
Published: (2025)

Enhancing ACPF Analysis: Integrating Newton-Raphson Method with Gradient Descent and Computational Graphs
by: Barati, Masoud
Published: (2024)

Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation
by: Cai, Yang, et al.
Published: (2023)

GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
by: Zeng, Hongtai, et al.
Published: (2024)

Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence
by: Deng, Yichuan, et al.
Published: (2024)

Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics
by: Jnini, Anas, et al.
Published: (2024)

Improving parton shower predictions via precision moments of energy flow polynomials
by: Assi, Benoît, et al.
Published: (2026)

Adaptive Accelerated Gradient Descent Methods for Convex Optimization
by: Xu, Zeyi, et al.
Published: (2026)

Decentralized Relaxed Smooth Optimization with Gradient Descent Methods
by: Jiang, Zhanhong, et al.
Published: (2025)

AI Agents Can Already Autonomously Perform Experimental High Energy Physics
by: Moreno, Eric A., et al.
Published: (2026)

Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization
by: Shen, Wei, et al.
Published: (2023)

Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
by: Karnik, Santhosh, et al.
Published: (2024)

The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
by: Harvey, Thomas R.
Published: (2025)

Finite-Time Analysis of Gradient Descent for Shallow Transformers
by: Arda, Enes, et al.
Published: (2026)

Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent
by: Hennick, Max, et al.
Published: (2025)

On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks
by: Gao, Yihang, et al.
Published: (2024)

On a Family of Relaxed Gradient Descent Methods for Quadratic Minimization
by: MacDonald, Liam, et al.
Published: (2024)

Generalized Stochastic Gradient Descent with Momentum Methods for Smooth Optimization
by: Wang, Zimeng, et al.
Published: (2026)

Computation of Quark Masses from String Theory
by: Constantin, Andrei, et al.
Published: (2024)

IRKA is a Riemannian Gradient Descent Method
by: Mlinarić, Petar, et al.
Published: (2023)

Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations
by: Crăciun, Alexandru, et al.
Published: (2025)

Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
by: Aolaritei, Liviu, et al.
Published: (2025)

Online Riemannian Gradient Descent for Quantum State Tomography with Matrix Product Operators
by: Cai, Jian-Feng, et al.
Published: (2026)

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
by: Khaled, Ahmed, et al.
Published: (2023)

Gauss-Newton Natural Gradient Descent for Shape Learning
by: King, James, et al.
Published: (2026)

Derivatives of Stochastic Gradient Descent in parametric optimization
by: Iutzeler, Franck, et al.
Published: (2024)

Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning
by: Descours, Arnaud, et al.
Published: (2025)

On Penalty-based Bilevel Gradient Descent Method
by: Shen, Han, et al.
Published: (2023)