Imagen de Portada

Learning to Discover Iterative Spectral Algorithms

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Zihang, Balabanov, Oleg, Yang, Yaoqing, Mahoney, Michael W.
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Numerical Analysis
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training
por: Yang, Shenghao, et al.
Publicado: (2026)

IFNSO: Iteration-Free Newton-Schulz Orthogonalization
por: Hu, Chen, et al.
Publicado: (2026)

AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures
por: Gao, Yihang, et al.
Publicado: (2024)

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
por: Pourkamali-Anaraki, Farhad
Publicado: (2026)

Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Study
por: Ke, Yekun, et al.
Publicado: (2024)

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
por: Wang, Hong, et al.
Publicado: (2025)

Beyond Loss Guidance: Using PDE Residuals as Spectral Attention in Diffusion Neural Operators
por: Sawhney, Medha, et al.
Publicado: (2025)

Spectral Estimation with Free Decompression
por: Ameli, Siavash, et al.
Publicado: (2025)

Free Decompression with Algebraic Spectral Curves
por: Ameli, Siavash, et al.
Publicado: (2026)

Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning
por: Dereziński, Michał, et al.
Publicado: (2024)

LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
por: Liu, Zihang, et al.
Publicado: (2025)

PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws
por: Yang, Liu, et al.
Publicado: (2024)

DeepContour: A Hybrid Deep Learning Framework for Accelerating Generalized Eigenvalue Problem Solving via Efficient Contour Design
por: Chen, Yeqiu, et al.
Publicado: (2025)

Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approach
por: Li, Guoming, et al.
Publicado: (2024)

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
por: Wang, Qi, et al.
Publicado: (2024)

A Mathematical Guide to Operator Learning
por: Boullé, Nicolas, et al.
Publicado: (2023)

Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
por: Yan, Mingsong, et al.
Publicado: (2026)

Projection Methods for Operator Learning and Universal Approximation
por: Zappala, Emanuele
Publicado: (2024)

Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis
por: Cheng, Long, et al.
Publicado: (2025)

Moving Sampling Physics-informed Neural Networks induced by Moving Mesh PDE
por: Yang, Yu, et al.
Publicado: (2023)

Mixture of Experts Softens the Curse of Dimensionality in Operator Learning
por: Kratsios, Anastasis, et al.
Publicado: (2024)

Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
por: Berner, Julius, et al.
Publicado: (2025)

Kinetic-based regularization: Learning spatial derivatives and PDE applications
por: Ganguly, Abhisek, et al.
Publicado: (2026)

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

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
por: Zhang, Ce, et al.
Publicado: (2023)

Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
por: Berman, Jules, et al.
Publicado: (2026)

Learning Semilinear Neural Operators : A Unified Recursive Framework For Prediction And Data Assimilation
por: Singh, Ashutosh, et al.
Publicado: (2024)

CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
por: Hou, Xianglong, et al.
Publicado: (2025)

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
por: Khodak, Mikhail, et al.
Publicado: (2023)

Observation-specific explanations through scattered data approximation
por: Ghidini, Valentina, et al.
Publicado: (2024)

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
por: Li, Rui, et al.
Publicado: (2024)

Physics-Informed Neural Networks for High-Frequency and Multi-Scale Problems using Transfer Learning
por: Mustajab, Abdul Hannan, et al.
Publicado: (2024)

AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
por: Du, Jianda, et al.
Publicado: (2026)

Sparse $L^1$-Autoencoders for Scientific Data Compression
por: Chung, Matthias, et al.
Publicado: (2024)

ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
por: Son, Hwijae
Publicado: (2025)

Spectral Informed Neural Network: An Efficient and Low-Memory PINN
por: Yu, Tianchi, et al.
Publicado: (2024)

V-ABFT: Variance-Based Adaptive Threshold for Fault-Tolerant Matrix Multiplication in Mixed-Precision Deep Learning
por: Gao, Yiheng, et al.
Publicado: (2026)

Autoregression-Free Neural Operators for Time-Dependent PDEs
por: Zhang, Jiaquan, et al.
Publicado: (2026)

KAN-GCN: Combining Kolmogorov-Arnold Network with Graph Convolution Network for an Accurate Ice Sheet Emulator
por: Liu, Zesheng, et al.
Publicado: (2025)

Quasi-Framelets: Robust Graph Neural Networks via Adaptive Framelet Convolution
por: Yang, Mengxi, et al.
Publicado: (2022)