Skip to content
AI News HubLIVE
Original source2 min read

When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization

Summary

arXiv:2609.30271v1 Announce Type: new Abstract: Adaptive optimizers are commonly parameterized by a fixed power of the second-moment estimate. Existing partially adaptive methods study exponents between momentum-like updates and the standard Adam square root, while the interaction between this exponent and the global learning rate is less understood. We perform a controlled cross-environment study using a paired four-environment classification problem with stable sparse features, environment-dependent spurious sparse features, dense features, and high-dimensional noise. Across \NumRuns{} source-training runs covering 21 preconditioning exponents $p\in[-0.5,0.5]$ and five learning rates $\eta\in[10^{-4},10^{-2}]$, we find that the exponent maximizing cross-environment accuracy decreases al…

SourcearXiv Machine LearningAuthor: Gongyue Zhang, Honghai Liu
When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization
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 25 Jul 2026]

Title:When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization

View a PDF of the paper titled When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization, by Gongyue Zhang and Honghai Liu

View PDF HTML (experimental)

Abstract:Adaptive optimizers are commonly parameterized by a fixed power of the second-moment estimate. Existing partially adaptive methods study exponents between momentum-like updates and the standard Adam square root, while the interaction between this exponent and the global learning rate is less understood. We perform a controlled cross-environment study using a paired four-environment classification problem with stable sparse features, environment-dependent spurious sparse features, dense features, and high-dimensional noise. Across \NumRuns{} source-training runs covering 21 preconditioning exponents $p\in[-0.5,0.5]$ and five learning rates $\eta\in[10^{-4},10^{-2}]$, we find that the exponent maximizing cross-environment accuracy decreases almost linearly with $\log_{10}\eta$. The fitted slopes range from $-0.270$ to $-0.300$, with $R^2$ between $0.972$ and $0.996$. At $\eta=10^{-2}$, source-validation selection still prefers positive exponents in all four environments, whereas cross-environment and worst-environment criteria prefer negative exponents. Checkpoint decomposition shows that lower $p$ reduces the learned spurious-to-stable and noise-to-stable weight ratios; under reversed correlation, it also reduces the magnitude of the harmful spurious margin. Negative $p$ is therefore not a universally optimal setting. It is a high-step-size allocation regime produced by the joint action of learning rate and preconditioning. The study also exposes a model-selection conflict: source-domain validation systematically selects a different preconditioning regime from the one that maximizes robustness to environmental change. The results are a single-seed, finite-budget mechanism study rather than a broad benchmark claim.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2609.30271 [cs.LG]

(or arXiv:2609.30271v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.30271

arXiv-issued DOI via DataCite

Submission history

From: Gongyue Zhang [view email] [v1] Sat, 25 Jul 2026 01:24:44 UTC (328 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled When the Preconditioning Exponent Turns Negative: Learning-Rate Coupling and Cross-Environment Generalization, by Gongyue Zhang and Honghai Liu

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

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

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.30271v1 Announce Type: new Abstract: Adaptive optimizers are commonly parameterized by a fixed power of the second-moment estimate. Existing partially adaptive methods…

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