Abstract:Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions under which personalized alignment achieves O(1) online regret and log(1/epsilon) offline sample complexity. We show that these optimal rates depend on a specific user-diversity condition: the population of user-specific heads must span the latent reward directions that can alter the optimal response. We prove that this condition is both necessary and sufficient. When it holds, simple greedy algorithms achieve benchmark efficiency; when it fails, every learner in a natural admissible class incurs at least logarithmic regret. Our results identify user diversity as the fundamental driver of personalized identifiability.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.09119 [cs.LG] |
| (or arXiv:2605.09119v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.09119 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Enoch Hyunwook Kang [view email]
[v1]
Sat, 9 May 2026 19:07:35 UTC (308 KB)