Image de couverture de livre

A Theoretical Framework for OOD Robustness in Transformers using Gevrey Classes

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yu, Chang, Fu-Chieh, Wu, Pei-Yuan
Format:	Preprint
Publié:	2025
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

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner
par: Chang, Fu-Chieh, et autres
Publié: (2024)

Unveiling the Latent Directions of Reflection in Large Language Models
par: Chang, Fu-Chieh, et autres
Publié: (2025)

Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
par: Montasser, Omar, et autres
Publié: (2024)

Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning
par: Lai, Yen-Ru, et autres
Publié: (2024)

Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures
par: Chang, Fu-Chieh, et autres
Publié: (2024)

CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network
par: Bai, Jia-Hau, et autres
Publié: (2024)

Bridging OOD Detection and Generalization: A Graph-Theoretic View
par: Wang, Han, et autres
Publié: (2024)

WeiPer: OOD Detection using Weight Perturbations of Class Projections
par: Granz, Maximilian, et autres
Publié: (2024)

An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning
par: Liu, Xingtu
Publié: (2025)

RankOOD -- Class Ranking-based Out-of-Distribution Detection
par: Denipitiyage, Dishanika, et autres
Publié: (2025)

GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model
par: Xu, Haoyan, et autres
Publié: (2025)

Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
par: Lee, Yu-Ting, et autres
Publié: (2025)

Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalization
par: Li, Yan, et autres
Publié: (2025)

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
par: Fu, Shaopeng, et autres
Publié: (2023)

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
par: Jiang, Liangze, et autres
Publié: (2024)

MetaOOD: Automatic Selection of OOD Detection Models
par: Qin, Yuehan, et autres
Publié: (2024)

M3OOD: Automatic Selection of Multimodal OOD Detectors
par: Qin, Yuehan, et autres
Publié: (2025)

DynaSubVAE: Adaptive Subgrouping for Scalable and Robust OOD Detection
par: Behrouzi, Tina, et autres
Publié: (2025)

Robust OOD Graph Learning via Mean Constraints and Noise Reduction
par: Zhou, Yang, et autres
Publié: (2025)

Decorr: Environment Partitioning for Invariant Learning and OOD Generalization
par: Liao, Yufan, et autres
Publié: (2022)

Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data
par: Mondal, Sudeepta, et autres
Publié: (2026)

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
par: Mao, Yixiu, et autres
Publié: (2024)

DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification
par: Han, Xiaoxue, et autres
Publié: (2024)

General-Purpose Multi-Modal OOD Detection Framework
par: Duong, Viet, et autres
Publié: (2023)

A Theoretical Framework for Modular Learning of Robust Generative Models
par: Cortes, Corinna, et autres
Publié: (2026)

What If the Input is Expanded in OOD Detection?
par: Zhang, Boxuan, et autres
Publié: (2024)

Influence-Guided Concolic Testing of Transformer Robustness
par: Hong, Chih-Duo, et autres
Publié: (2025)

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
par: Hu, Jerry Yao-Chieh, et autres
Publié: (2024)

Exponential Expressivity of ReLU$^k$ Neural Networks on Gevrey Classes with Point Singularities
par: Opschoor, Joost A. A., et autres
Publié: (2024)

An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise
par: Cui, Jingyi, et autres
Publié: (2025)

TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection
par: Yu, Yuan-Cheng, et autres
Publié: (2025)

Invariant Random Forest: Tree-Based Model Solution for OOD Generalization
par: Liao, Yufan, et autres
Publié: (2023)

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
par: Kim, Donghwan, et autres
Publié: (2026)

Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood
par: Yao, Qingmao, et autres
Publié: (2025)

Score Combining for Contrastive OOD Detection
par: Reehorst, Edward T., et autres
Publié: (2025)

Intermediate Layer Classifiers for OOD generalization
par: Uselis, Arnas, et autres
Publié: (2025)

A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts
par: Nakada, Ryumei, et autres
Publié: (2025)

A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
par: Lee, Chungpa, et autres
Publié: (2025)

Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models
par: Shen, Xu, et autres
Publié: (2024)

A Theoretical Analysis of the Learning Dynamics under Class Imbalance
par: Francazi, Emanuele, et autres
Publié: (2022)