Image de couverture de livre

Understanding Generalization from Embedding Dimension and Distributional Convergence

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Junjie, Ouyang, Zhuoli, Deng, Haotian, Wei, Chen, Ma, Wenxiao, Zhang, Jianyu, Deng, Zihan, Liu, Quanying
Format:	Preprint
Publié:	2026
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

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

Scale-Invariance Drives Convergence in AI and Brain Representations
par: Yu, Junjie, et autres
Publié: (2025)

Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
par: Yu, Junjie, et autres
Publié: (2026)

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation
par: Deng, Shenyang, et autres
Publié: (2026)

RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
par: Deng, Shenyang, et autres
Publié: (2026)

Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis
par: Deng, Shenyang, et autres
Publié: (2026)

On the Convergence and Stability of Distributed Sub-model Training
par: Deng, Yuyang, et autres
Publié: (2025)

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents
par: Zhang, Menglong, et autres
Publié: (2024)

Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressions
par: Deng, Haotian, et autres
Publié: (2025)

Self-Supervised Graph Embedding Clustering
par: Li, Fangfang, et autres
Publié: (2024)

Optimal Stochastic Trace Estimation in Generative Modeling
par: Liu, Xinyang, et autres
Publié: (2025)

Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback
par: Chen, Shulun, et autres
Publié: (2025)

Forecasting Epileptic Seizures from Contactless Camera via Cross-Species Transfer Learning
par: Zhai, Mingkai, et autres
Publié: (2026)

A Combination Model Based on Sequential General Variational Mode Decomposition Method for Time Series Prediction
par: Chen, Wei, et autres
Publié: (2024)

Salutary Labeling with Zero Human Annotation
par: Xiao, Wenxiao, et autres
Publié: (2024)

DCHO: A Decomposition-Composition Framework for Predicting Higher-Order Brain Connectivity to Enhance Diverse Downstream Applications
par: Li, Weibin, et autres
Publié: (2025)

FuncGenFoil: Airfoil Generation and Editing Model in Function Space
par: Zhang, Jinouwen, et autres
Publié: (2025)

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
par: Qian, Fuyuan, et autres
Publié: (2026)

Adaptive SGD with Line-Search and Polyak Stepsizes: Nonconvex Convergence and Accelerated Rates
par: Wu, Haotian
Publié: (2025)

Optimal Convergence Rates of Deep Neural Network Classifiers
par: Zhang, Zihan, et autres
Publié: (2025)

Balance of Number of Embedding and their Dimensions in Vector Quantization
par: Chen, Hang, et autres
Publié: (2024)

GEM: Empowering LLM for both Embedding Generation and Language Understanding
par: Zhang, Caojin, et autres
Publié: (2025)

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory
par: Niu, Xueyan, et autres
Publié: (2024)

Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
par: Jiang, Wei, et autres
Publié: (2025)

MaskBit: Embedding-free Image Generation via Bit Tokens
par: Weber, Mark, et autres
Publié: (2024)

Knowledge Distillation with Adapted Weight
par: Wu, Sirong, et autres
Publié: (2025)

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

DimGrow: Memory-Efficient Field-level Embedding Dimension Search
par: Huang, Yihong, et autres
Publié: (2025)

Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting
par: Gao, Haotian, et autres
Publié: (2023)

Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization
par: Chen, Yang, et autres
Publié: (2024)

Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees
par: Deng, Yuyang, et autres
Publié: (2024)

Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
par: Liu, Yuhao, et autres
Publié: (2025)

Reflected Schrödinger Bridge for Constrained Generative Modeling
par: Deng, Wei, et autres
Publié: (2024)

Understanding Generalization through Decision Pattern Shift
par: Deng, Huiqi, et autres
Publié: (2026)

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

Enhanced semi-supervised stamping process monitoring with physically-informed feature extraction
par: Zhang, Jianyu
Publié: (2025)

Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning
par: Gan, Kai, et autres
Publié: (2024)

Optimal Convergence Analysis of DDPM for General Distributions
par: Jiao, Yuchen, et autres
Publié: (2025)

On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks
par: Liu, Xin, et autres
Publié: (2023)

MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites
par: Zhang, Heng, et autres
Publié: (2026)