Copertina

Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hsu, Alexander, Shen, Zhaiming, Liao, Wenjing, Lai, Rongjie
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Numerical Analysis
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights
di: Shen, Zhaiming, et al.
Pubblicazione: (2025)

Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods
di: Shen, Zhaiming, et al.
Pubblicazione: (2025)

Data-Driven Model Reduction using WeldNet: Windowed Encoders for Learning Dynamics
di: Dahal, Biraj, et al.
Pubblicazione: (2025)

Maximal Volume Matrix Cross Approximation for Image Compression and Least Squares Solution
di: Allen, Kenneth, et al.
Pubblicazione: (2023)

Graph-based Semi-supervised Local Clustering with Few Labeled Nodes
di: Shen, Zhaiming, et al.
Pubblicazione: (2022)

Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders
di: Schonsheck, Stefan C., et al.
Pubblicazione: (2022)

Learn to Evolve: Self-supervised Neural JKO Operator for Wasserstein Gradient Flow
di: Feng, Xue, et al.
Pubblicazione: (2026)

The Kolmogorov Superposition Theorem can Break the Curse of Dimensionality When Approximating High Dimensional Functions
di: Lai, Ming-Jun, et al.
Pubblicazione: (2021)

The Optimal Linear B-splines Approximation via Kolmogorov Superposition Theorem and its Application
di: Lai, Ming-Jun, et al.
Pubblicazione: (2024)

Deep Learning for Subspace Regression
di: Fanaskov, Vladimir, et al.
Pubblicazione: (2025)

Cauchy Random Features for Operator Learning in Sobolev Space
di: Liao, Chunyang, et al.
Pubblicazione: (2025)

Solving Partial Differential Equations with Random Feature Models
di: Liao, Chunyang
Pubblicazione: (2024)

DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
di: Hao, Zhongkai, et al.
Pubblicazione: (2024)

Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
di: Jalalian, Yasamin, et al.
Pubblicazione: (2025)

Nonlocality and Nonlinearity Implies Universality in Operator Learning
di: Lanthaler, Samuel, et al.
Pubblicazione: (2023)

In-Context Operator Learning on the Space of Probability Measures
di: Cole, Frank, et al.
Pubblicazione: (2026)

Single-shot prediction of parametric partial differential equations
di: Rafiq, Khalid, et al.
Pubblicazione: (2025)

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

Deriving Transformer Architectures as Implicit Multinomial Regression
di: Actor, Jonas A., et al.
Pubblicazione: (2025)

Operator Learning at Machine Precision
di: Bacho, Aras, et al.
Pubblicazione: (2025)

One-Shot Transfer Learning for Nonlinear PDEs with Perturbative PINNs
di: Auroy, Samuel, et al.
Pubblicazione: (2025)

Machine Learning-Based Nonlinear Nudging for Chaotic Dynamical Systems
di: Oh, Jaemin, et al.
Pubblicazione: (2025)

Solving All Regression Models For Learning Gaussian Networks Using Givens Rotations
di: Alipourfard, Borzou, et al.
Pubblicazione: (2019)

In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning
di: Cole, Frank, et al.
Pubblicazione: (2024)

FAST: Factorizable Attention for Speeding up Transformers
di: Gerami, Armin, et al.
Pubblicazione: (2024)

Nonlinear model reduction for operator learning
di: Eivazi, Hamidreza, et al.
Pubblicazione: (2024)

A Novel Methodology in Credit Spread Prediction Based on Ensemble Learning and Feature Selection
di: Shao, Yu, et al.
Pubblicazione: (2024)

Neural Parameter Regression for Explicit Representations of PDE Solution Operators
di: Mundinger, Konrad, et al.
Pubblicazione: (2024)

Continuum Attention for Neural Operators
di: Calvello, Edoardo, et al.
Pubblicazione: (2024)

Regression-aware decompositions
di: Tygert, Mark
Pubblicazione: (2017)

Scalable Bayesian Inference for Nonlinear Conservation Laws
di: Weiland, Tim, et al.
Pubblicazione: (2026)

Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression
di: Ghahari, Farid
Pubblicazione: (2026)

Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers
di: Pförtner, Marvin, et al.
Pubblicazione: (2022)

Quantitative Approximation for Neural Operators in Nonlinear Parabolic Equations
di: Furuya, Takashi, et al.
Pubblicazione: (2024)

Spectral Audit of In-Context Operator Networks
di: Gao, Zhiwei, et al.
Pubblicazione: (2026)

Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
di: Chen, Junfeng, et al.
Pubblicazione: (2024)

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

Long-time Integration of Nonlinear Wave Equations with Neural Operators
di: Lei, Guanhang, et al.
Pubblicazione: (2024)

TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs
di: Chen, Yanlai, et al.
Pubblicazione: (2024)

Solving Nonlinear PDEs with Sparse Radial Basis Function Networks
di: Shao, Zihan, et al.
Pubblicazione: (2025)