Bose, A., Xiong, Z., Saha, A., Du, S. S., & Fazel, M. (2024). Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration.
Chicago Style (17th ed.) CitationBose, Avinandan, Zhihan Xiong, Aadirupa Saha, Simon Shaolei Du, and Maryam Fazel. Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration. 2024.
MLA (9th ed.) CitationBose, Avinandan, et al. Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration. 2024.
Warning: These citations may not always be 100% accurate.