| title | A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics |
|---|---|
| authors | Zixi Li, Youzhen Li |
| date | 2026-05-07 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.06741 |
| affiliation | Reasoning Kingdom |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Learning-rate steps are usually treated as hyperparameters. This paper isolates a local beliefspace calculation: when an update is modeled as a projected forward step on the probability simplex, admissibility means contractivity in the natural KL/Bregman geometry. Under this model, the upper bound of an admissible step is not a tuning slogan but a formula. |
cite
@misc{li2026closed,
title={A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics},
author={Zixi Li and Youzhen Li},
year={2026},
eprint={2605.06741},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.06741}
}