arxiv:2605.06741

A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics

Published on May 7

· Submitted by

Authors:

Abstract

Admissibility in learning-rate steps is characterized by contractivity in KL/Bregman geometry, providing a formulaic upper bound rather than a tunable parameter.

AI-generated summary

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.

View arXiv page View PDF Add to collection

Community

OzTianlu

Paper submitter about 8 hours ago

Learning-rate steps are usually treated as hyperparameters. This paper isolates a local belief-space 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.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

Get this paper in your agent:

hf papers read 2605.06741

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.06741 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.06741 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.06741 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.