Skip to content
AI News HubLIVE
Original source2 min read

Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle

Summary

This paper studies quantum minimum finding for layer-group learning-rate selection in a hybrid classical-quantum training framework, comparing fixed-budget and confidence-based stopping policies and introducing an Interaction-Guided Schedule Oracle that scores joint schedules in superposition without a precomputed score table. In closed-loop fine-tuning of a 1.5-billion-parameter language model, each selected schedule drives 200 classical steps and benchmark accuracies fall within the range seen across five uniform-rate seeds.

SourcearXiv Machine LearningAuthor: Wei-Che Hung
Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 16 Nov 2026]

Title:Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle

View a PDF of the paper titled Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle, by Wei-Che Hung

View PDF HTML (experimental)

Abstract:Learning-rate choices strongly affect language-model fine-tuning, but the best joint profile across layer groups is generally unknown. This paper studies quantum minimum finding for layer-group learning-rate selection within a hybrid classical-quantum training framework. It combines Durr-Hoyer minimum finding with BBHT search and compares fixed-budget and confidence-based stopping policies using a lookup oracle built from measured profile scores at fixed training checkpoints. The paper then introduces an Interaction-Guided Schedule Oracle that scores and marks joint schedules in superposition without a precomputed score table. Classical one-step loss measurements supply the main, pairwise and three-way interaction effects between layer groups. The circuit adds the effects for each schedule, compares the resulting score with the current baseline score, and marks improving schedules for amplitude amplification. Measured candidates are checked classically before acceptance. Uniform-rate training supplies the initial baseline; using schedules from classical adaptive methods as baselines for joint refinement is left for future work. In closed-loop fine-tuning of a 1.5-billion-parameter language model, each selected schedule drives the next 200 classical training steps. Benchmark accuracies lie within the range observed across five uniform-rate seeds. The results give a working example of how quantum superposition can support adaptive learning-rate selection during training; the remaining quantum limitations are discussed in the paper.

Comments: 10 figures, 11 tables (including appendices)

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2611.21701 [cs.LG]

(or arXiv:2611.21701v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.21701

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Wei-Che Hung [view email] [v1] Mon, 16 Nov 2026 15:39:21 UTC (191 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle, by Wei-Che Hung

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Combines Dürr-Høyer minimum finding with BBHT search and compares fixed-budget versus confidence-based stopping.
  • The Interaction-Guided Schedule Oracle uses classical one-step loss measurements to derive main, pairwise, and three-way interaction effects, then marks improving schedules for amplitude amplification.
  • Closed-loop experiments on a 1.5B-parameter model run 200 classical steps per selected schedule, with accuracy comparable to uniform-rate baselines.

Highlights and analysis are generated automatically and may contain errors. Check the original source.