Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yang, Yang, Long, Liang, Yitao, Lin, Zhouchen
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Limitations and Capabilities of Position Embeddings for Length Generalization
di: Chen, Yang, et al.
Pubblicazione: (2025)

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
di: Chen, Yang, et al.
Pubblicazione: (2024)

Understanding Generalization from Embedding Dimension and Distributional Convergence
di: Yu, Junjie, et al.
Pubblicazione: (2026)

General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
di: Lai, Kuo-Wei, et al.
Pubblicazione: (2023)

Golden Ratio-Based Sufficient Dimension Reduction
di: Yang, Wenjing, et al.
Pubblicazione: (2024)

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
di: Chakraborty, Saptarshi, et al.
Pubblicazione: (2024)

Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs
di: Liang, Zhangyong, et al.
Pubblicazione: (2026)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
di: Marshall, Noah, et al.
Pubblicazione: (2024)

Scalable Importance Sampling in High Dimensions with Low-Rank Mixture Proposals
di: Kruse, Liam A., et al.
Pubblicazione: (2025)

On Conditional Stochastic Interpolation for Generative Nonlinear Sufficient Dimension Reduction
di: Xu, Shuntuo, et al.
Pubblicazione: (2025)

Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula
di: Vilucchio, Matteo, et al.
Pubblicazione: (2025)

Dimension-Free Saddle-Point Escape in Muon
di: Long, Yanlin, et al.
Pubblicazione: (2026)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions
di: Schmidt, Jonathan, et al.
Pubblicazione: (2023)

Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
di: Chen, Yang, et al.
Pubblicazione: (2024)

Sparse Semantic Dimension as a Generalization Certificate for LLMs
di: Bandyopadhyay, Dibyanayan, et al.
Pubblicazione: (2026)

On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
di: Yu, Bing, et al.
Pubblicazione: (2020)

Generalized Robust Adaptive-Bandwidth Multi-View Manifold Learning in High Dimensions with Noise
di: Ding, Xiucai, et al.
Pubblicazione: (2026)

On the Limitations of Fractal Dimension as a Measure of Generalization
di: Tan, Charlie B., et al.
Pubblicazione: (2024)

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

Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
di: Yu, Junjie, et al.
Pubblicazione: (2026)

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

The No-Clash Teaching Dimension is Bounded by VC Dimension
di: Liu, Jiahua, et al.
Pubblicazione: (2026)

Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
di: Chen, Yifan, et al.
Pubblicazione: (2024)

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
di: Schliserman, Matan, et al.
Pubblicazione: (2024)

Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation
di: Sapkota, Suman, et al.
Pubblicazione: (2023)

Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization
di: Li, Huan, et al.
Pubblicazione: (2021)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
di: Sun, Yan, et al.
Pubblicazione: (2025)

Vanilla Bayesian Optimization Performs Great in High Dimensions
di: Hvarfner, Carl, et al.
Pubblicazione: (2024)

Pruning is Optimal for Learning Sparse Features in High-Dimensions
di: Vural, Nuri Mert, et al.
Pubblicazione: (2024)

Rethinking Trust Region Bayesian Optimization in High Dimensions
di: Tang, Wei-Ting, et al.
Pubblicazione: (2026)

An Observation on Lloyd's k-Means Algorithm in High Dimensions
di: Silva-Sánchez, David, et al.
Pubblicazione: (2025)

Bridging Dimensions: Confident Reachability for High-Dimensional Controllers
di: Geng, Yuang, et al.
Pubblicazione: (2023)

Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
di: Chandrasekaran, Gautam, et al.
Pubblicazione: (2024)

Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension
di: Klivans, Adam R., et al.
Pubblicazione: (2026)

Invariant Kernels: Rank Stabilization and Generalization Across Dimensions
di: Díaz, Mateo, et al.
Pubblicazione: (2025)

On the Saturation Effects of Spectral Algorithms in Large Dimensions
di: Lu, Weihao, et al.
Pubblicazione: (2025)

Dimension-free Private Mean Estimation for Anisotropic Distributions
di: Dagan, Yuval, et al.
Pubblicazione: (2024)

Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
di: Zakerinia, Hossein, et al.
Pubblicazione: (2025)

Exact Risk Curves of signSGD in High-Dimensions: Quantifying Preconditioning and Noise-Compression Effects
di: Xiao, Ke Liang, et al.
Pubblicazione: (2024)

Non-Asymptotic Length Generalization
di: Chen, Thomas, et al.
Pubblicazione: (2025)