Skip to content
AI News HubLIVE
Original source2 min read

Near-Quadratic Sample Compression for All VC Classes

Summary

Researchers construct a sample compression scheme of size O(d^2 log^2 d) for every binary concept class of VC dimension d, proving the weaker Floyd–Warmuth sample compression conjecture; only exponential bounds were previously known.

SourcearXiv Machine LearningAuthor: Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw, Aranyak Mehta, Shay Moran, Grigoris Velegkas, Di Wang, Manfred K. Warmuth
Near-Quadratic Sample Compression for All VC Classes
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 18 Nov 2026]

Title:Near-Quadratic Sample Compression for All VC Classes

View a PDF of the paper titled Near-Quadratic Sample Compression for All VC Classes, by Yang Cai and 8 other authors

View PDF HTML (experimental)

Abstract:The sample compression conjecture is a longstanding open problem in learning theory, originating in the work of Littlestone and Warmuth in the 1980s. At its heart is a connection between simplification and generalization: if a predictor consistent with a training sample is defined using only a small part of that sample, then it is likely to generalize. Sample compression schemes formalize this idea, and many natural learning algorithms can be analyzed this way.

The sample compression conjecture of Floyd and Warmuth (1995) asserts that every binary concept class of VC dimension $d$ admits a sample compression scheme of size $O(d)$; a weaker conjecture asks only for size polynomial in $d$. Both have remained open: the first bound depending only on $d$, due to Moran and Yehudayoff (2016), is exponential in $d$. We prove the weaker conjecture by constructing a sample compression scheme of size $O(d^2 \log^2 d)$.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Data Structures and Algorithms (cs.DS); Combinatorics (math.CO); Machine Learning (stat.ML)

Cite as: arXiv:2611.25011 [cs.LG]

(or arXiv:2611.25011v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.25011

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Grigoris Velegkas [view email] [v1] Wed, 18 Nov 2026 18:57:23 UTC (41 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Near-Quadratic Sample Compression for All VC Classes, by Yang Cai and 8 other authors

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 cs.AI cs.DS math math.CO stat stat.ML

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

ResearchersAdvanced

Key points

  • The paper proves that every binary concept class of VC dimension d admits a sample compression scheme of size O(d^2 log^2 d).
  • This resolves the weaker form of the sample compression conjecture, which asks only for polynomial size, while the stronger O(d) bound remains open.
  • The best previous bound depending only on d was exponential and due to Moran and Yehudayoff (2016).
  • The work connects simplification and generalization and widens the range of algorithms analyzable via compression schemes.

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