Image de couverture de livre

Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Yang, Yang, Long, Liang, Yitao, Lin, Zhouchen
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Limitations and Capabilities of Position Embeddings for Length Generalization
par: Chen, Yang, et autres
Publié: (2025)

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
par: Chen, Yang, et autres
Publié: (2024)

Understanding Generalization from Embedding Dimension and Distributional Convergence
par: Yu, Junjie, et autres
Publié: (2026)

General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
par: Lai, Kuo-Wei, et autres
Publié: (2023)

Golden Ratio-Based Sufficient Dimension Reduction
par: Yang, Wenjing, et autres
Publié: (2024)

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
par: Chakraborty, Saptarshi, et autres
Publié: (2024)

Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs
par: Liang, Zhangyong, et autres
Publié: (2026)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
par: Marshall, Noah, et autres
Publié: (2024)

Scalable Importance Sampling in High Dimensions with Low-Rank Mixture Proposals
par: Kruse, Liam A., et autres
Publié: (2025)

On Conditional Stochastic Interpolation for Generative Nonlinear Sufficient Dimension Reduction
par: Xu, Shuntuo, et autres
Publié: (2025)

Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula
par: Vilucchio, Matteo, et autres
Publié: (2025)

Dimension-Free Saddle-Point Escape in Muon
par: Long, Yanlin, et autres
Publié: (2026)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions
par: Schmidt, Jonathan, et autres
Publié: (2023)

Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
par: Chen, Yang, et autres
Publié: (2024)

Sparse Semantic Dimension as a Generalization Certificate for LLMs
par: Bandyopadhyay, Dibyanayan, et autres
Publié: (2026)

On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
par: Yu, Bing, et autres
Publié: (2020)

Generalized Robust Adaptive-Bandwidth Multi-View Manifold Learning in High Dimensions with Noise
par: Ding, Xiucai, et autres
Publié: (2026)

On the Limitations of Fractal Dimension as a Measure of Generalization
par: Tan, Charlie B., et autres
Publié: (2024)

Stochastic-Dimension Frozen Sampled Neural Network for High-Dimensional Gross-Pitaevskii Equations on Unbounded Domains
par: Liang, Zhangyong
Publié: (2026)

Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
par: Yu, Junjie, et autres
Publié: (2026)

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

The No-Clash Teaching Dimension is Bounded by VC Dimension
par: Liu, Jiahua, et autres
Publié: (2026)

Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
par: Chen, Yifan, et autres
Publié: (2024)

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
par: Schliserman, Matan, et autres
Publié: (2024)

Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization
par: Li, Huan, et autres
Publié: (2021)

Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation
par: Sapkota, Suman, et autres
Publié: (2023)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
par: Sun, Yan, et autres
Publié: (2025)

Vanilla Bayesian Optimization Performs Great in High Dimensions
par: Hvarfner, Carl, et autres
Publié: (2024)

Pruning is Optimal for Learning Sparse Features in High-Dimensions
par: Vural, Nuri Mert, et autres
Publié: (2024)

Rethinking Trust Region Bayesian Optimization in High Dimensions
par: Tang, Wei-Ting, et autres
Publié: (2026)

An Observation on Lloyd's k-Means Algorithm in High Dimensions
par: Silva-Sánchez, David, et autres
Publié: (2025)

Bridging Dimensions: Confident Reachability for High-Dimensional Controllers
par: Geng, Yuang, et autres
Publié: (2023)

Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
par: Chandrasekaran, Gautam, et autres
Publié: (2024)

Invariant Kernels: Rank Stabilization and Generalization Across Dimensions
par: Díaz, Mateo, et autres
Publié: (2025)

Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension
par: Klivans, Adam R., et autres
Publié: (2026)

On the Saturation Effects of Spectral Algorithms in Large Dimensions
par: Lu, Weihao, et autres
Publié: (2025)

Dimension-free Private Mean Estimation for Anisotropic Distributions
par: Dagan, Yuval, et autres
Publié: (2024)

Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
par: Zakerinia, Hossein, et autres
Publié: (2025)

Exact Risk Curves of signSGD in High-Dimensions: Quantifying Preconditioning and Noise-Compression Effects
par: Xiao, Ke Liang, et autres
Publié: (2024)

Non-Asymptotic Length Generalization
par: Chen, Thomas, et autres
Publié: (2025)