Image de couverture de livre

On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kamber, Anil, Parhi, Rahul
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sharpness of Minima in Deep Matrix Factorization
par: Kamber, Anil, et autres
Publié: (2025)

Towards Sharp Minimax Risk Bounds for Operator Learning
par: Adcock, Ben, et autres
Publié: (2025)

A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization
par: Chen, Po, et autres
Publié: (2025)

Generalization Below the Edge of Stability: The Role of Data Geometry
par: Liang, Tongtong, et autres
Publié: (2025)

Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities
par: Parhi, Rahul, et autres
Publié: (2023)

Finding Stable Subnetworks at Initialization with Dataset Distillation
par: McDermott, Luke, et autres
Publié: (2025)

Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
par: Pritchard, Henry, et autres
Publié: (2025)

Sharp Minima Can Generalize: A Loss Landscape Perspective On Data
par: Fan, Raymond, et autres
Publié: (2025)

A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
par: Kumar, Akash, et autres
Publié: (2025)

Model Merging on Loss Landscape: A Geometry Perspective
par: Lu, Juanwu, et autres
Publié: (2026)

Implicit Regularization in Perturbed Deep Matrix Factorization: Spectral Conditions and Stability
par: Wang, Jingzhe, et autres
Publié: (2026)

Monge SAM: Robust Reparameterization-Invariant Sharpness-Aware Minimization Based on Loss Geometry
par: Jacobsen, Albert Kjøller, et autres
Publié: (2025)

Matrix Sensing with Kernel Optimal Loss: Robustness and Optimization Landscape
par: Song, Xinyuan, et autres
Publié: (2025)

Early-Warning Signals of Grokking via Loss-Landscape Geometry
par: Xu, Yongzhong
Publié: (2026)

Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
par: Bai, Zhiwei, et autres
Publié: (2024)

Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
par: Shenouda, Joseph, et autres
Publié: (2023)

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
par: Liang, Tongtong, et autres
Publié: (2025)

Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
par: Xu, Yichu, et autres
Publié: (2024)

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term
par: Yue, Yun, et autres
Publié: (2023)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
par: Bai, Zhiwei, et autres
Publié: (2022)

LoLA: Low-Rank Linear Attention With Sparse Caching
par: McDermott, Luke, et autres
Publié: (2025)

Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
par: Liang, Tongtong, et autres
Publié: (2026)

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
par: Fang, Kun, et autres
Publié: (2023)

Sensitivity Analysis On Loss Landscape
par: Faroz, Salman
Publié: (2024)

A Regularization-Sharpness Tradeoff for Linear Interpolators
par: Hu, Qingyi, et autres
Publié: (2026)

Persistent Nonnegative Matrix Factorization via Multi-Scale Graph Regularization
par: Zhang, Jichao, et autres
Publié: (2026)

Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
par: Zou, Jinping, et autres
Publié: (2024)

Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
par: Sun, Yan, et autres
Publié: (2023)

Loss Landscape Geometry and the Learning of Symmetries: Or, What Influence Functions Reveal About Robust Generalization
par: Amarel, James, et autres
Publié: (2026)

Random ReLU Neural Networks as Non-Gaussian Processes
par: Parhi, Rahul, et autres
Publié: (2024)

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
par: Zhao, Heyang, et autres
Publié: (2024)

Neural Network Plasticity and Loss Sharpness
par: Koster, Max, et autres
Publié: (2024)

Low-Rank Matrix Factorizations with Volume-based Constraints and Regularizations
par: Thanh, Olivier Vu
Publié: (2024)

LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization
par: Teng, Yunfei, et autres
Publié: (2025)

Weighted variation spaces and approximation by shallow ReLU networks
par: DeVore, Ronald, et autres
Publié: (2023)

Approximating Matrix Functions with Deep Neural Networks and Transformers
par: Padmanabhan, Rahul, et autres
Publié: (2026)

There is a Singularity in the Loss Landscape
par: Lowell, Mark
Publié: (2022)

Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
par: Li, Xinghan, et autres
Publié: (2025)

Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
par: Matveev, Maria, et autres
Publié: (2025)

Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
par: Li, Bingcong, et autres
Publié: (2024)