Copertina

How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yurong, He, Yu, Jordan, Michael I., Yao, Fan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computer Science and Game Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Calibeating Made Simple
di: Chen, Yurong, et al.
Pubblicazione: (2026)

Response Time Enhances Alignment with Heterogeneous Preferences
di: Echenique, Federico, et al.
Pubblicazione: (2026)

One-Shot Strategic Classification Under Unknown Costs
di: Rosenfeld, Elan, et al.
Pubblicazione: (2023)

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications
di: Cai, Yang, et al.
Pubblicazione: (2025)

Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation
di: Cai, Yang, et al.
Pubblicazione: (2023)

Fair Allocation in Dynamic Mechanism Design
di: Fallah, Alireza, et al.
Pubblicazione: (2024)

Defection-Free Collaboration between Competitors in a Learning System
di: Werner, Mariel, et al.
Pubblicazione: (2024)

Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence
di: Wu, Jiduan, et al.
Pubblicazione: (2023)

Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
di: Shi, Zhekun, et al.
Pubblicazione: (2025)

A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design
di: Ai, Rui, et al.
Pubblicazione: (2022)

Incentive-Theoretic Bayesian Inference for Collaborative Science
di: Bates, Stephen, et al.
Pubblicazione: (2023)

Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
di: Scheid, Antoine, et al.
Pubblicazione: (2024)

Last-Iterate Convergence of Payoff-Based Independent Learning in Zero-Sum Stochastic Games
di: Chen, Zaiwei, et al.
Pubblicazione: (2024)

Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach
di: Qiu, Shuang, et al.
Pubblicazione: (2022)

NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
di: Yu, Eason, et al.
Pubblicazione: (2025)

Is Thompson Sampling Susceptible to Algorithmic Collusion?
di: Xiong, Yi, et al.
Pubblicazione: (2024)

Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
di: Cai, Yang, et al.
Pubblicazione: (2023)

Last-Iterate Convergence of No-Regret Learning for Equilibria in Bargaining Games
di: Kamp, Serafina, et al.
Pubblicazione: (2025)

Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback
di: Jordan, Michael I., et al.
Pubblicazione: (2023)

Efficient Last-Iterate Convergence in Regret Minimization via Adaptive Reward Transformation
di: Ren, Hang, et al.
Pubblicazione: (2025)

Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?
di: Ahmadi, Saba, et al.
Pubblicazione: (2025)

Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
di: Maiti, Arnab, et al.
Pubblicazione: (2026)

Incentivized Learning in Principal-Agent Bandit Games
di: Scheid, Antoine, et al.
Pubblicazione: (2024)

Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
di: Jordan, Philip, et al.
Pubblicazione: (2026)

On Separation Between Best-Iterate, Random-Iterate, and Last-Iterate Convergence of Learning in Games
di: Cai, Yang, et al.
Pubblicazione: (2025)

Towards Sustainable Investment Policies Informed by Opponent Shaping
di: Duque, Juan Agustin, et al.
Pubblicazione: (2026)

Distributional Alignment Games for Answer-Level Fine-Tuning
di: Mohri, Mehryar, et al.
Pubblicazione: (2026)

Incentivizing High-Quality Content in Online Recommender Systems
di: Hu, Xinyan, et al.
Pubblicazione: (2023)

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
di: Jagadeesan, Meena, et al.
Pubblicazione: (2023)

Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
di: Gölz, Paul, et al.
Pubblicazione: (2025)

Independent Learning in Constrained Markov Potential Games
di: Jordan, Philip, et al.
Pubblicazione: (2024)

How to Evaluate Behavioral Models
di: d'Eon, Greg, et al.
Pubblicazione: (2023)

State-Constrained Zero-Sum Differential Games with One-Sided Information
di: Ghimire, Mukesh, et al.
Pubblicazione: (2024)

Analysing the Sample Complexity of Opponent Shaping
di: Fung, Kitty, et al.
Pubblicazione: (2024)

Clickbait vs. Quality: How Engagement-Based Optimization Shapes the Content Landscape in Online Platforms
di: Immorlica, Nicole, et al.
Pubblicazione: (2024)

Are Bounded Contracts Learnable and Approximately Optimal?
di: Chen, Yurong, et al.
Pubblicazione: (2024)

How Market Volatility Shapes Algorithmic Collusion: A Comparative Analysis of Learning-Based Pricing Algorithms
di: Sravon, Aheer, et al.
Pubblicazione: (2025)

Refined Sample Complexity for Markov Games with Independent Linear Function Approximation
di: Dai, Yan, et al.
Pubblicazione: (2024)

Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Losses
di: Lu, Jiuyao, et al.
Pubblicazione: (2025)

Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
di: Schiffer, Benjamin, et al.
Pubblicazione: (2025)