Copertina

Solving Inverse Problems with Deep Linear Neural Networks: Global Convergence Guarantees for Gradient Descent with Weight Decay

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Laus, Hannah, Parkinson, Suzanna, Charisopoulos, Vasileios, Krahmer, Felix, Willett, Rebecca
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Nonlinear tomographic reconstruction via nonsmooth optimization
di: Charisopoulos, Vasileios, et al.
Pubblicazione: (2024)

Faster Adaptive Optimization via Expected Gradient Outer Product Reparameterization
di: DePavia, Adela, et al.
Pubblicazione: (2025)

ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models
di: Parkinson, Suzanna, et al.
Pubblicazione: (2023)

A Model-Guided Neural Network Method for the Inverse Scattering Problem
di: Tsang, Olivia, et al.
Pubblicazione: (2025)

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

Local linear convergence of gradient methods for overparameterized Gaussian mixtures
di: Wang, Jingxing, et al.
Pubblicazione: (2026)

Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
di: Beneventano, Pierfrancesco, et al.
Pubblicazione: (2025)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
di: Kassing, Sebastian, et al.
Pubblicazione: (2025)

Triangle Steepest Descent: A Geometry-Based Gradient Algorithm with Guaranteed R-Linear Convergence
di: Shen, Ya, et al.
Pubblicazione: (2025)

Open Problem: Anytime Convergence Rate of Gradient Descent
di: Kornowski, Guy, et al.
Pubblicazione: (2024)

Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
di: Cayci, Semih, et al.
Pubblicazione: (2024)

How do simple rotations affect the implicit bias of Adam?
di: DePavia, Adela, et al.
Pubblicazione: (2025)

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
di: Jung, Hyunji, et al.
Pubblicazione: (2025)

Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
di: Xu, Xianliang, et al.
Pubblicazione: (2024)

Last-Iterate Convergence of Anchored Gradient Descent
di: Cai, Yang, et al.
Pubblicazione: (2026)

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

Depth Separation in Norm-Bounded Infinite-Width Neural Networks
di: Parkinson, Suzanna, et al.
Pubblicazione: (2024)

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
di: Ganesh, Swetha, et al.
Pubblicazione: (2024)

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

Plugging Weight-tying Nonnegative Neural Network into Proximal Splitting Method: Architecture for Guaranteeing Convergence to Optimal Point
di: Shimizu, Haruya, et al.
Pubblicazione: (2025)

Decentralized Sparse Linear Regression via Gradient-Tracking: Linear Convergence and Statistical Guarantees
di: Maros, Marie, et al.
Pubblicazione: (2022)

Multi-Frequency Progressive Refinement for Learned Inverse Scattering
di: Melia, Owen, et al.
Pubblicazione: (2024)

A Proof of the Exact Convergence Rate of Gradient Descent
di: Kim, Jungbin
Pubblicazione: (2024)

High-Probability Guarantees for Random Zeroth-Order (Stochastic) Gradient Descent
di: Ye, Haishan
Pubblicazione: (2026)

Learning Provably Improves the Convergence of Gradient Descent
di: Song, Qingyu, et al.
Pubblicazione: (2025)

Convergence of Alternating Gradient Descent for Matrix Factorization
di: Ward, Rachel, et al.
Pubblicazione: (2023)

Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks
di: Qin, Zhen, et al.
Pubblicazione: (2023)

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

High-Probability Guarantees for Random Zeroth-Order Gradient Descent on Smooth Functions
di: Ye, Haishan
Pubblicazione: (2026)

Convergence of Policy Gradient for Stochastic Linear-Quadratic Control Problem in Infinite Horizon
di: Zhang, Xinpei, et al.
Pubblicazione: (2024)

Accelerated Objective Gap and Gradient Norm Convergence for Gradient Descent via Long Steps
di: Grimmer, Benjamin, et al.
Pubblicazione: (2024)

Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
di: Jaffe, Sean, et al.
Pubblicazione: (2024)

On Convergence of the Iteratively Preconditioned Gradient-Descent (IPG) Observer
di: Chakrabarti, Kushal, et al.
Pubblicazione: (2024)

Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators
di: Li, Tianyou, et al.
Pubblicazione: (2023)

On the Convergence of Gradient Descent on Learning Transformers with Residual Connections
di: Qin, Zhen, et al.
Pubblicazione: (2025)

Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning
di: Caron, Francois, et al.
Pubblicazione: (2023)

Effective Front-Descent Algorithms with Convergence Guarantees
di: Lapucci, Matteo, et al.
Pubblicazione: (2024)

Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
di: Hayta, Berk, et al.
Pubblicazione: (2026)

Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
di: Martínez-Rubio, David, et al.
Pubblicazione: (2024)

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
di: Cai, Yuhang, et al.
Pubblicazione: (2025)