FlashKAN: B-Spline KANs via Truncated Power Form
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
arXiv:2609.01956 (cs)
[Submitted on 2 Sep 2026]
Title:FlashKAN: B-Spline KANs via Truncated Power Form
Authors:Naveen Mysore
View a PDF of the paper titled FlashKAN: B-Spline KANs via Truncated Power Form, by Naveen Mysore
View PDF
HTML (experimental)
Abstract:Kolmogorov-Arnold Networks (KANs) place learnable B-spline activations on network edges rather than fixed activations on nodes. The standard Cox-de Boor recursion evaluates these activations through k sequential passes for degree-k splines, consuming over 90% of forward-pass time. FlashKAN replaces this recursion with the truncated power form, a classical result from approximation theory that expresses each uniform cubic B-spline as five (x)_+^3 terms at shifted knot positions. This paper makes three contributions: (1) a this http URL-fused implementation that collapses these operations into a single GPU kernel, eliminating all recursion, span lookup, and scatter-gather operations; (2) a bounded-coordinate stabilization that clamps the normalized input to [0, k+1], preventing the catastrophic cancellation that historically motivated the Cox-de Boor recursion; and (3) a production-ready, open-source package (pip install flashkan) that serves as a drop-in replacement for existing KAN layers.
| Comments: | 7 pages, 1 table, under review at ICLR 2027 |
| Subjects: | Machine Learning (cs.LG); Numerical Analysis (math.NA) |
| MSC classes: | 68T07, 65D07, 41A15 |
| ACM classes: | I.2.6; G.1.1 |
| Cite as: | arXiv:2609.01956 [cs.LG] |
| (or arXiv:2609.01956v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.01956
arXiv-issued DOI via DataCite (pending registration)
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled FlashKAN: B-Spline KANs via Truncated Power Form, by Naveen Mysore
Current browse context:
cs.LG
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
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 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
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
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?)
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.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.