Imagen de Portada

Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Min, Hancheng, Vidal, René
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Systems and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
por: Min, Hancheng, et al.
Publicado: (2025)

A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models
por: Xu, Ziqing, et al.
Publicado: (2025)

Learning safety critics via a non-contractive binary bellman operator
por: Castellano, Agustin, et al.
Publicado: (2024)

Domain-decoupled Physics-informed Neural Networks with Closed-form Gradients for Fast Model Learning of Dynamical Systems
por: Krauss, Henrik, et al.
Publicado: (2024)

Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization
por: Xu, Ziqing, et al.
Publicado: (2025)

Convergence Rates for Gradient Descent on the Edge of Stability in Overparametrised Least Squares
por: MacDonald, Lachlan Ewen, et al.
Publicado: (2025)

Safe Gradient Flow for Bilevel Optimization
por: Sharifi, Sina, et al.
Publicado: (2025)

ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares
por: Min, Youngjae, et al.
Publicado: (2022)

AoI-Aware Task Offloading and Transmission Optimization for Industrial IoT Networks: A Branching Deep Reinforcement Learning Approach
por: Chen, Yuang, et al.
Publicado: (2025)

An ADRC-Incorporated Stochastic Gradient Descent Algorithm for Latent Factor Analysis
por: Li, Jinli, et al.
Publicado: (2024)

Heat Death of Generative Models in Closed-Loop Learning
por: Marchi, Matteo, et al.
Publicado: (2024)

A Test-Function Approach to Incremental Stability
por: Pfrommer, Daniel, et al.
Publicado: (2025)

Deep Q-Learning with Gradient Target Tracking
por: Park, Bum Geun, et al.
Publicado: (2025)

Learning AC Power Flow Solutions using a Data-Dependent Variational Quantum Circuit
por: Le, Thinh Viet, et al.
Publicado: (2025)

Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning
por: Davydov, Alexander
Publicado: (2025)

Approximate Gradient Coding for Distributed Learning with Heterogeneous Stragglers
por: Song, Heekang, et al.
Publicado: (2025)

Gradient Flow Equations for Deep Linear Neural Networks: A Survey from a Network Perspective
por: Wendin, Joel, et al.
Publicado: (2025)

Incremental Correction in Dynamic Systems Modelled with Neural Networks for Constraint Satisfaction
por: Cho, Namhoon, et al.
Publicado: (2022)

Reinforcement Learning of Structured Control for Linear Systems with Unknown State Matrix
por: Mukherjee, Sayak, et al.
Publicado: (2020)

Can Implicit Bias Imply Adversarial Robustness?
por: Min, Hancheng, et al.
Publicado: (2024)

Time-Series-Informed Closed-loop Learning for Sequential Decision Making and Control
por: Hirt, Sebastian, et al.
Publicado: (2024)

A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning
por: Chakrabarti, Kushal, et al.
Publicado: (2022)

Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning
por: Khattar, Vanshaj, et al.
Publicado: (2024)

Safe and Stable Closed-Loop Learning for Neural-Network-Supported Model Predictive Control
por: Hirt, Sebastian, et al.
Publicado: (2024)

Dynamic Importance Learning using Fisher Information Matrix (FIM) for Nonlinear Dynamic Mapping
por: Eivaghi, Vahid MohammadZadeh, et al.
Publicado: (2024)

On The Convergence of Euler Discretization of Finite-Time Convergent Gradient Flows
por: Zhang, Siqi, et al.
Publicado: (2020)

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
por: Li, Zeyang, et al.
Publicado: (2026)

Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning
por: Town, Jared, et al.
Publicado: (2022)

A Hierarchical Surrogate Model for Efficient Multi-Task Parameter Learning in Closed-Loop Control
por: Hirt, Sebastian, et al.
Publicado: (2025)

Scaling Laws of Machine Learning for Optimal Power Flow
por: Liu, Xinyi, et al.
Publicado: (2026)

Learning the Optimal Power Flow: Environment Design Matters
por: Wolgast, Thomas, et al.
Publicado: (2024)

High-Dimensional Surrogate Modeling for Closed-Loop Learning of Neural-Network-Parameterized Model Predictive Control
por: Hirt, Sebastian, et al.
Publicado: (2025)

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

Gradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planning
por: Li, Shihao, et al.
Publicado: (2026)

Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions
por: Za'ter, Muhy Eddin, et al.
Publicado: (2025)

On the Gradient Domination of the LQG Problem
por: Fallah, Kasra, et al.
Publicado: (2025)

Anytime Acceleration of Gradient Descent
por: Zhang, Zihan, et al.
Publicado: (2024)

Closed-Loop Koopman Operator Approximation
por: Dahdah, Steven, et al.
Publicado: (2023)

Beyond the Neural Fog: Interpretable Learning for AC Optimal Power Flow
por: Pineda, Salvador, et al.
Publicado: (2024)

Investigating the Impact of Observation Space Design Choices On Training Reinforcement Learning Solutions for Spacecraft Problems
por: Hamilton, Nathaniel, et al.
Publicado: (2025)