Copertina

Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Bum Jun, N'guessan, Gnankan Landry Regis
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks
di: N'guessan, Gnankan Landry Regis, et al.
Pubblicazione: (2026)

Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities
di: N'guessan, Gnankan Landry Regis, et al.
Pubblicazione: (2026)

EqOD: Symmetry-Informed Stability Selection for PDE Identification
di: N'guessan, Gnankan Landry Regis, et al.
Pubblicazione: (2026)

Müntz-Szász Networks: Neural Architectures with Learnable Power-Law Bases
di: N'guessan, Gnankan Landry Regis
Pubblicazione: (2025)

v-PuNNs: van der Put Neural Networks for Transparent Ultrametric Representation Learning
di: N'guessan, Gnankan Landry Regis
Pubblicazione: (2025)

FI-KAN: Fractal Interpolation Kolmogorov-Arnold Networks
di: N'guessan, Gnankan Landry Regis
Pubblicazione: (2026)

PALMA: A Lightweight Tropical Algebra Library for ARM-Based Embedded Systems
di: N'guessan, Gnankan Landry Regis
Pubblicazione: (2026)

Localized Weather Prediction Using Kolmogorov-Arnold Network-Based Models and Deep RNNs
di: Akazan, Ange-Clement, et al.
Pubblicazione: (2025)

The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness
di: N'guessan, Gnankan Landry Regis, et al.
Pubblicazione: (2025)

Architecture-Optimization Co-Design for Physics-Informed Neural Networks Via Attentive Representations and Conflict-Resolved Gradients
di: Niu, Pancheng, et al.
Pubblicazione: (2026)

Temperature-Free Loss Function for Contrastive Learning
di: Kim, Bum Jun, et al.
Pubblicazione: (2025)

Exactness Matters for Physical Rule Enforcement
di: Kim, Bum Jun
Pubblicazione: (2026)

Estimation de la relation d’Okun pour la Côte d’Ivoire
di: Coffie Francis José N'guessan
Pubblicazione: (2019)

The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
di: Kim, Bum Jun, et al.
Pubblicazione: (2024)

Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations
di: Dashtbayaz, Nima Hosseini, et al.
Pubblicazione: (2024)

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
di: Liu, Qiang, et al.
Pubblicazione: (2024)

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning
di: Pirayeshshirazinezhad, Reza
Pubblicazione: (2026)

Exploring Physics-Informed Neural Networks for Crop Yield Loss Forecasting
di: Miranda, Miro, et al.
Pubblicazione: (2024)

On the Duality between Gradient Transformations and Adapters
di: Torroba-Hennigen, Lucas, et al.
Pubblicazione: (2025)

Learning from Integral Losses in Physics Informed Neural Networks
di: Saleh, Ehsan, et al.
Pubblicazione: (2023)

Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators
di: Gan, Weiye, et al.
Pubblicazione: (2025)

Convergence Analysis of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
di: Xu, Xianliang, et al.
Pubblicazione: (2024)

FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
di: Yu, Hongyeon, et al.
Pubblicazione: (2026)

Preconditioning for Physics-Informed Neural Networks
di: Liu, Songming, et al.
Pubblicazione: (2024)

GradINN: Gradient Informed Neural Network
di: Aglietti, Filippo, et al.
Pubblicazione: (2024)

LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
di: Kim, Hyunjun
Pubblicazione: (2026)

Ensemble learning for Physics Informed Neural Networks: a Gradient Boosting approach
di: Fang, Zhiwei, et al.
Pubblicazione: (2023)

Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks
di: Jnini, Anas, et al.
Pubblicazione: (2025)

HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters
di: Mo, Yujie, et al.
Pubblicazione: (2024)

Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks
di: Jin, Bangti, et al.
Pubblicazione: (2025)

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

Preventing Conflicting Gradients in Neural Marked Temporal Point Processes
di: Bosser, Tanguy, et al.
Pubblicazione: (2024)

Conformalized Physics-Informed Neural Networks
di: Podina, Lena, et al.
Pubblicazione: (2024)

Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
di: Chou, Yi En, et al.
Pubblicazione: (2025)

Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
di: Hwang, Youngsik, et al.
Pubblicazione: (2024)

Revising the Structure of Recurrent Neural Networks to Eliminate Numerical Derivatives in Forming Physics Informed Loss Terms with Respect to Time
di: Jahani-nasab, Mahyar, et al.
Pubblicazione: (2024)

Taming Gradient Oversmoothing and Expansion in Graph Neural Networks
di: Park, MoonJeong, et al.
Pubblicazione: (2024)

Towards Scalable Bayesian Optimization via Gradient-Informed Bayesian Neural Networks
di: Makrygiorgos, Georgios, et al.
Pubblicazione: (2025)

Complex Physics-Informed Neural Network
di: Si, Chenhao, et al.
Pubblicazione: (2025)

Physics-Informed Neural Networks and Extensions
di: Raissi, Maziar, et al.
Pubblicazione: (2024)