Image de couverture de livre

Uniformly Stable Algorithms for Adversarial Training and Beyond

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xiao, Jiancong, Zhang, Jiawei, Luo, Zhi-Quan, Ozdaglar, Asuman
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

Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
par: Kim, Kihyun, et autres
Publié: (2025)

Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints
par: Ozdaglar, Asuman, et autres
Publié: (2022)

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
par: Kim, Kihyun, et autres
Publié: (2024)

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
par: Park, Chanwoo, et autres
Publié: (2023)

UFT: Unifying Supervised and Reinforcement Fine-Tuning
par: Liu, Mingyang, et autres
Publié: (2025)

LiteEFG: An Efficient Python Library for Solving Extensive-form Games
par: Liu, Mingyang, et autres
Publié: (2024)

A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence
par: Liu, Mingyang, et autres
Publié: (2024)

Differentially Private Equilibrium Finding in Polymatrix Games
par: Liu, Mingyang, et autres
Publié: (2025)

The Power of Regularization in Solving Extensive-Form Games
par: Liu, Mingyang, et autres
Publié: (2022)

What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
par: Bennouna, Omar, et autres
Publié: (2025)

Computing Equilibrium beyond Unilateral Deviation
par: Liu, Mingyang, et autres
Publié: (2026)

Do LLM Agents Have Regret? A Case Study in Online Learning and Games
par: Park, Chanwoo, et autres
Publié: (2024)

RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation
par: Park, Chanwoo, et autres
Publié: (2024)

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
par: Zhang, Jiawei, et autres
Publié: (2020)

Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games
par: Faizal, Fathima Zarin, et autres
Publié: (2024)

Last-Iterate Convergence of Payoff-Based Independent Learning in Zero-Sum Stochastic Games
par: Chen, Zaiwei, et autres
Publié: (2024)

Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
par: Zhang, Runyu, et autres
Publié: (2025)

Learning Decision-Sufficient Representations for Linear Optimization
par: Ye, Yuhan, et autres
Publié: (2026)

Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms
par: Pournaderi, Mehrdad, et autres
Publié: (2024)

Online Learning and Equilibrium Computation with Ranking Feedback
par: Liu, Mingyang, et autres
Publié: (2026)

Preserving Diversity in Supervised Fine-Tuning of Large Language Models
par: Li, Ziniu, et autres
Publié: (2024)

Matching of Users and Creators in Two-Sided Markets with Departures
par: Huttenlocher, Daniel, et autres
Publié: (2023)

Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
par: Xu, Tian, et autres
Publié: (2022)

On the Escaping Efficiency of Distributed Adversarial Training Algorithms
par: Cao, Ying, et autres
Publié: (2025)

Addressing misspecification in contextual optimization
par: Bennouna, Omar, et autres
Publié: (2024)

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
par: Li, Yingru, et autres
Publié: (2024)

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization
par: Xiao, Jiancong, et autres
Publié: (2024)

On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
par: Xiao, Jiancong, et autres
Publié: (2024)

Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
par: Jin, Ruochen, et autres
Publié: (2024)

Uniform Convergence Beyond Glivenko-Cantelli
par: Devale, Tanmay, et autres
Publié: (2025)

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
par: Chen, Luoyu, et autres
Publié: (2026)

Data-Dependent Stability Analysis of Adversarial Training
par: Wang, Yihan, et autres
Publié: (2024)

Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
par: Park, Chanwoo, et autres
Publié: (2025)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
par: Li, Long-Fei, et autres
Publié: (2024)

Efficient Optimization Algorithms for Linear Adversarial Training
par: RIbeiro, Antônio H., et autres
Publié: (2024)

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
par: Liu, Chen, et autres
Publié: (2021)

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
par: Liang, Hao, et autres
Publié: (2022)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
par: Huang, Kezhao, et autres
Publié: (2023)

Scalable Exploration via Ensemble++
par: Li, Yingru, et autres
Publié: (2024)

UMOEA/D: A Multiobjective Evolutionary Algorithm for Uniform Pareto Objectives based on Decomposition
par: Zhang, Xiaoyuan, et autres
Publié: (2024)