Image de couverture de livre

Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dong, Yijun, Li, Yicheng, Li, Yunai, Lee, Jason D., Lei, Qi
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Numerical Analysis
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
par: Dong, Yijun, et autres
Publié: (2024)

Neural Low-Discrepancy Sequences
par: Van Huffel, Michael Etienne, et autres
Publié: (2025)

Learned Discrepancy Reconstruction and Benchmark Dataset for Magnetic Particle Imaging
par: Iske, Meira, et autres
Publié: (2025)

Low Stein Discrepancy via Message-Passing Monte Carlo
par: Kirk, Nathan, et autres
Publié: (2025)

Weak Physics Informed Neural Networks for Geometry Compatible Hyperbolic Conservation Laws on Manifolds
par: Zhou, Hanfei, et autres
Publié: (2025)

Tensor Completion with Nearly Linear Samples Given Weak Side Information
par: Yu, Christina Lee, et autres
Publié: (2020)

Intrinsic Dimension Estimating Autoencoder (IDEA) Using CancelOut Layer and a Projected Loss
par: Oriou, Antoine, et autres
Publié: (2025)

A Generative Sampler for distributions with possible discrete parameter based on Reversibility
par: Li, Lei, et autres
Publié: (2026)

A Probabilistic Framework for Solving High-Frequency Helmholtz Equations via Diffusion Models
par: Zou, Yicheng, et autres
Publié: (2026)

Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
par: Zhou, Junru, et autres
Publié: (2025)

Optimizing Kernel Discrepancies via Subset Selection
par: Chen, Deyao, et autres
Publié: (2025)

Convergence analysis of OT-Flow for sample generation
par: Jing, Yang, et autres
Publié: (2024)

Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening
par: Li, Guoming, et autres
Publié: (2025)

Symmetry group based domain decomposition to enhance physics-informed neural networks for solving partial differential equations
par: Liu, Ye, et autres
Publié: (2024)

On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions
par: Lu, Yulong, et autres
Publié: (2025)

Dimension reduction for derivative-informed operator learning: An analysis of approximation errors
par: Luo, Dingcheng, et autres
Publié: (2025)

Fast Kernel Summation in High Dimensions via Slicing and Fourier Transforms
par: Hertrich, Johannes
Publié: (2024)

Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
par: Li, Gen, et autres
Publié: (2025)

Sparsity via Hyperpriors: A Theoretical and Algorithmic Study under Empirical Bayes Framework
par: Li, Zhitao, et autres
Publié: (2025)

Large Data Limits of Laplace Learning for Gaussian Measure Data in Infinite Dimensions
par: Zhong, Zhengang, et autres
Publié: (2026)

Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions
par: Niu, Chengmei, et autres
Publié: (2026)

Stochastic Dimension Implicit Functional Projections for Exact Integral Conservation in High-Dimensional PINNs
par: Liang, Zhangyong
Publié: (2026)

Weak Form Scientific Machine Learning: Test Function Construction for System Identification
par: Tran, April, et autres
Publié: (2025)

PINNsFailureRegion Localization and Refinement through White-box AdversarialAttack
par: Shi, Shengzhu, et autres
Publié: (2023)

WINO: A Weak-Form Physics Informed Neural Operator for Hyperelasticity on Variable Domains
par: Zhu, Bokai, et autres
Publié: (2026)

Optimal Embedding Dimension for Sparse Subspace Embeddings
par: Chenakkod, Shabarish, et autres
Publié: (2023)

Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy
par: Xie, Peichen, et autres
Publié: (2025)

Long-time Integration of Nonlinear Wave Equations with Neural Operators
par: Lei, Guanhang, et autres
Publié: (2024)

Learning Singularity-Encoded Green's Functions with Application to Iterative Methods
par: Sun, Qi, et autres
Publié: (2025)

Monotone Generative Modeling via a Gromov-Monge Embedding
par: Lee, Wonjun, et autres
Publié: (2023)

Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spaces
par: Cheng, Zilan, et autres
Publié: (2026)

Fourier Neural Operator with Learned Deformations for PDEs on General Geometries
par: Li, Zongyi, et autres
Publié: (2022)

An Efficient Deep Learning Approach for Approximating Parameter-to-Solution Maps of PDEs
par: Lei, Guanhang, et autres
Publié: (2024)

Sharp Convergence Rates for Matching Pursuit
par: Klusowski, Jason M., et autres
Publié: (2023)

Enhanced BPINN Training Convergence in Solving General and Multi-scale Elliptic PDEs with Noise
par: Hou, Yilong, et autres
Publié: (2024)

Efficient Differentiable Approximation of Generalized Low-rank Regularization
par: Li, Naiqi, et autres
Publié: (2025)

Geometry-Preserving Encoder/Decoder in Latent Generative Models
par: Lee, Wonjun, et autres
Publié: (2025)

GeoFunFlow-3D: A Physics-Guided Generative Flow Matching Framework for High-Fidelity 3D Aerodynamic Inference over Complex Geometries
par: Jiang, Ruiling, et autres
Publié: (2026)

A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning
par: Yang, Jia-Qi, et autres
Publié: (2025)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
par: Zhan, Zhiyuan, et autres
Publié: (2026)