Cover Image

Challenges in Training PINNs: A Loss Landscape Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rathore, Pratik, Lei, Weimu, Frangella, Zachary, Lu, Lu, Udell, Madeleine
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
by: Frangella, Zachary, et al.
Published: (2022)

PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates
by: Frangella, Zachary, et al.
Published: (2023)

Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
by: Rathore, Pratik, et al.
Published: (2025)

Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
by: Rathore, Pratik, et al.
Published: (2024)

On the (linear) convergence of Generalized Newton Inexact ADMM
by: Frangella, Zachary, et al.
Published: (2023)

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

GeNIOS: an (almost) second-order operator-splitting solver for large-scale convex optimization
by: Diamandis, Theo, et al.
Published: (2023)

CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
by: Feng, Miria, et al.
Published: (2024)

Gradient Methods with Online Scaling
by: Gao, Wenzhi, et al.
Published: (2024)

Gradient Methods with Online Scaling Part I. Theoretical Foundations
by: Gao, Wenzhi, et al.
Published: (2025)

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
by: Chu, Ya-Chi, et al.
Published: (2025)

Gradient Methods with Online Scaling Part II. Practical Aspects
by: Chu, Ya-Chi, et al.
Published: (2025)

Understanding Fixed Predictions via Confined Regions
by: Lawless, Connor, et al.
Published: (2025)

Enhancing Physics-Informed Neural Networks Through Feature Engineering
by: Fazliani, Shaghayegh, et al.
Published: (2025)

SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning
by: Sun, Jingruo, et al.
Published: (2025)

Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
by: Yoon, Hoyeol, et al.
Published: (2026)

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

Loss Landscape Characterization of Neural Networks without Over-Parametrization
by: Islamov, Rustem, et al.
Published: (2024)

Algebraic characterization of equivalence between oracle-based iterative algorithms
by: Lessard, Laurent, et al.
Published: (2025)

PINNs in PDE Constrained Optimal Control Problems: Direct vs Indirect Methods
by: Zhang, Zhen, et al.
Published: (2026)

The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach
by: Song, Yongcun, et al.
Published: (2023)

On Dissipativity of Cross-Entropy Loss in Training ResNets
by: Püttschneider, Jens, et al.
Published: (2024)

A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives
by: Nguyen, Ti Ti, et al.
Published: (2025)

Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity
by: Kong, Boao, et al.
Published: (2024)

An automatic system to detect equivalence between iterative algorithms
by: Zhao, Shipu, et al.
Published: (2021)

A Theoretical and Empirical Study on the Convergence of Adam with an "Exact" Constant Step Size in Non-Convex Settings
by: Mazumder, Alokendu, et al.
Published: (2023)

Towards an Optimal Control Perspective of ResNet Training
by: Püttschneider, Jens, et al.
Published: (2025)

Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
by: Li, Binghui, et al.
Published: (2026)

A Framework for Bilevel Optimization on Riemannian Manifolds
by: Han, Andi, et al.
Published: (2024)

Riemannian coordinate descent algorithms on matrix manifolds
by: Han, Andi, et al.
Published: (2024)

FedSEA: Achieving Benefit of Parallelization in Federated Online Learning
by: Sahu, Harekrushna, et al.
Published: (2026)

Riemannian Optimization for Hadamard Products of Low-Rank Matrices
by: Jawanpuria, Pratik, et al.
Published: (2026)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
by: Tanguy, Eloi
Published: (2023)

MMD-Regularized Unbalanced Optimal Transport
by: Manupriya, Piyushi, et al.
Published: (2020)

Learning Rate Schedules in the Presence of Distribution Shift
by: Fahrbach, Matthew, et al.
Published: (2023)

Accelerated Optimization Landscape of Linear-Quadratic Regulator
by: Feng, Lechen, et al.
Published: (2023)

First and Second Order Approximations to Stochastic Gradient Descent Methods with Momentum Terms
by: Lu, Eric
Published: (2025)

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

A Covering Framework for Offline POMDPs Learning using Belief Space Metric
by: Zhu, Youheng, et al.
Published: (2026)

When Does Primal Interior Point Method Beat Primal-dual in Linear Optimization?
by: Gao, Wenzhi, et al.
Published: (2024)