Image de couverture de livre

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yeom, Taesun, Ha, Taehyeok, Lee, Jaeho
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

On the Internal Representations of Graph Metanetworks
par: Yeom, Taesun, et autres
Publié: (2025)

Fast Training of Sinusoidal Neural Fields via Scaling Initialization
par: Yeom, Taesun, et autres
Publié: (2024)

Activation Quantization of Vision Encoders Needs Prefixing Registers
par: Kim, Seunghyeon, et autres
Publié: (2025)

Pluralistic Alignment Over Time
par: Klassen, Toryn Q., et autres
Publié: (2024)

Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features
par: Zhang, Junpeng, et autres
Publié: (2024)

Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning
par: Caron, Francois, et autres
Publié: (2023)

Over-the-Air Semantic Alignment with Stacked Intelligent Metasurfaces
par: Pandolfo, Mario Edoardo, et autres
Publié: (2025)

Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling
par: Nguyen, Phuc Minh, et autres
Publié: (2025)

Machine Learning-Assisted Thermoelectric Cooling for On-Demand Multi-Hotspot Thermal Management
par: Luo, Jiajian, et autres
Publié: (2024)

Position: Don't be Afraid of Over-Smoothing And Over-Squashing
par: Kormann, Niklas, et autres
Publié: (2026)

Diagonal Over-parameterization in Reproducing Kernel Hilbert Spaces as an Adaptive Feature Model: Generalization and Adaptivity
par: Li, Yicheng, et autres
Publié: (2025)

Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
par: Fu, Guoji, et autres
Publié: (2023)

On the Benefits of Over-parameterization for Out-of-Distribution Generalization
par: Hao, Yifan, et autres
Publié: (2024)

Understanding Likelihood Over-optimisation in Direct Alignment Algorithms
par: Shi, Zhengyan, et autres
Publié: (2024)

Inverse Feasibility in Over-the-Air Federated Learning
par: Piotrowski, Tomasz, et autres
Publié: (2022)

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
par: Arroyo, Álvaro, et autres
Publié: (2025)

Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
par: Zhu, Ting, et autres
Publié: (2024)

Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA
par: Lee, Sangyoon, et autres
Publié: (2026)

Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
par: Fesser, Lukas, et autres
Publié: (2023)

The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
par: Son, Seungwoo, et autres
Publié: (2023)

CAFO: Feature-Centric Explanation on Time Series Classification
par: Kim, Jaeho, et autres
Publié: (2024)

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
par: Ha, SeungBum, et autres
Publié: (2025)

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
par: Zhu, Yanqiao, et autres
Publié: (2023)

Causal Adjacency Learning for Spatiotemporal Prediction Over Graphs
par: Mo, Zhaobin, et autres
Publié: (2024)

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
par: Jamadandi, Adarsh, et autres
Publié: (2024)

FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
par: Lin, Runqi, et autres
Publié: (2025)

Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning
par: Khan, Fazal Muhammad Ali, et autres
Publié: (2024)

TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
par: Kim, Jaeho, et autres
Publié: (2025)

Simplifying the Theory on Over-Smoothing
par: Roth, Andreas
Publié: (2024)

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
par: Bombari, Simone, et autres
Publié: (2025)

Communication-Efficient Split Learning via Adaptive Feature-Wise Compression
par: Oh, Yongjeong, et autres
Publié: (2023)

Unsupervisedly Learned Representations: Should the Quest be Over?
par: Nissani, Daniel N.
Publié: (2020)

Learning Over Dirty Data with Minimal Repairs
par: Zhen, Cheng, et autres
Publié: (2025)

Learned Digital Codes for Over-the-Air Federated Learning
par: Tarizzo, Antonio, et autres
Publié: (2025)

Rethinking Federated Learning Over the Air: The Blessing of Scaling Up
par: Zhu, Jiaqi, et autres
Publié: (2025)

Nesterov-Accelerated Robust Federated Learning Over Byzantine Adversaries
par: Xu, Lihan, et autres
Publié: (2025)

Causal Contrastive Learning for Counterfactual Regression Over Time
par: Bouchattaoui, Mouad El, et autres
Publié: (2024)

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing
par: Sun, Li, et autres
Publié: (2024)

The Optimization Landscape of SGD Across the Feature Learning Strength
par: Atanasov, Alexander, et autres
Publié: (2024)

Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels
par: Liu, Hang, et autres
Publié: (2023)