Image de couverture de livre

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xing, Yue, Lin, Xiaofeng, Song, Qifan, Xu, Yi, Zeng, Belinda, Cheng, Guang
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

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data
par: Xing, Yue, et autres
Publié: (2024)

Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility
par: Haldar, Rajdeep, et autres
Publié: (2024)

Task-tailored Pre-processing: Fair Downstream Supervised Learning
par: Sohn, Jinwon, et autres
Publié: (2026)

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
par: Haldar, Rajdeep, et autres
Publié: (2024)

Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training
par: Wu, Zihui, et autres
Publié: (2022)

f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
par: Haldar, Rajdeep, et autres
Publié: (2026)

How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?
par: Liu, Meiqi, et autres
Publié: (2025)

On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
par: Li, Binghui, et autres
Publié: (2023)

Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes
par: Sohn, Jinwon, et autres
Publié: (2023)

Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
par: Zhou, MingWei, et autres
Publié: (2025)

LLM Safety Alignment is Divergence Estimation in Disguise
par: Haldar, Rajdeep, et autres
Publié: (2025)

Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders
par: Lei, Zhuxin, et autres
Publié: (2026)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
par: Javanmard, Adel, et autres
Publié: (2026)

Parallelly Tempered Generative Adversarial Nets: Toward Stabilized Gradients
par: Sohn, Jinwon, et autres
Publié: (2024)

Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective
par: Hu, Haichen, et autres
Publié: (2025)

Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
par: Yi, Bongsoo, et autres
Publié: (2024)

HGAN-SDEs: Learning Neural Stochastic Differential Equations with Hermite-Guided Adversarial Training
par: Xu, Yuanjian, et autres
Publié: (2025)

When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study
par: Yan, Jun, et autres
Publié: (2026)

Stability and Generalization in Free Adversarial Training
par: Cheng, Xiwei, et autres
Publié: (2024)

Latent Adversarial Training Improves the Representation of Refusal
par: Abbas, Alexandra, et autres
Publié: (2025)

CTSyn: A Foundation Model for Cross Tabular Data Generation
par: Lin, Xiaofeng, et autres
Publié: (2024)

Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training
par: Pan, Yuhao, et autres
Publié: (2025)

Information-Theoretic Policy Pre-Training with Empowerment
par: Schneider, Moritz, et autres
Publié: (2025)

Better Training Data Attribution via Better Inverse Hessian-Vector Products
par: Wang, Andrew, et autres
Publié: (2025)

OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
par: Song, Haiyue, et autres
Publié: (2026)

Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
par: Ye, Han-Jia, et autres
Publié: (2023)

Information Theoretic Adversarial Training of Large Language Models
par: Zhang, Yiwei, et autres
Publié: (2026)

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
par: Zhang, Guibin, et autres
Publié: (2024)

HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters
par: Mo, Yujie, et autres
Publié: (2024)

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

Towards a Better Theoretical Understanding of Independent Subnetwork Training
par: Shulgin, Egor, et autres
Publié: (2023)

FairRR: Pre-Processing for Group Fairness through Randomized Response
par: Zeng, Xianli, et autres
Publié: (2024)

Scaling Adversarial Training via Data Selection
par: Ye, Youran, et autres
Publié: (2025)

Adversarial Training from Mean Field Perspective
par: Kumano, Soichiro, et autres
Publié: (2025)

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
par: Wang, Ziyi, et autres
Publié: (2025)

Representation Learning of Multivariate Time Series using Attention and Adversarial Training
par: Scharwächter, Leon, et autres
Publié: (2024)

Adjustment for Confounding using Pre-Trained Representations
par: Schulte, Rickmer, et autres
Publié: (2025)

An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
par: Yoon, Jaesik, et autres
Publié: (2023)

Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization
par: Liu, Ganlin, et autres
Publié: (2024)

Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
par: Lu, Haoye, et autres
Publié: (2025)