@article{hybridpreferenceoptimizationforalignment, title = {Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration}, author = {Avinandan Bose and Zhihan Xiong and Aadirupa Saha and Simon Shaolei Du and Maryam Fazel}, year = {2024}, eprint = {2412.10616}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10616v1}, }