{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:43:01Z","timestamp":1782999781728,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800535","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"1102-1114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PolyKAN: A High-Performance and Universal GPU Operator Library for Polynomial Kolmogorov-Arnold Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3593-9032","authenticated-orcid":false,"given":"Mingkun","family":"Yu","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9825-3181","authenticated-orcid":false,"given":"Heming","family":"Zhong","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1417-3012","authenticated-orcid":false,"given":"Jiazhi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-1031","authenticated-orcid":false,"given":"Dan","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-3375","authenticated-orcid":false,"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, GuangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Hans\u00a0M Aus and Granino\u00a0A Korn. 2006. Table-lookup\/interpolation function generation for fixed-point digital computations. IEEE Trans. Comput. 100 8 (2006) 745\u2013749."},{"key":"e_1_3_3_1_3_2","unstructured":"Subhransu\u00a0S. Bhattacharjee. 2024. TorchKAN: Simplified KAN Model with Variations. GitHub repository. https:\/\/github.com\/1ssb\/torchkan"},{"key":"e_1_3_3_1_4_2","unstructured":"Alexander\u00a0Dylan Bodner Antonio\u00a0Santiago Tepsich Jack\u00a0Natan Spolski and Santiago Pourteau. 2024. Convolutional kolmogorov-arnold networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.13155 (2024)."},{"key":"e_1_3_3_1_5_2","unstructured":"Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro and Evan Shelhamer. 2014. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1410.0759 (2014)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"George Cybenko. 1989. Approximation by superpositions of a sigmoidal function. Mathematics of control signals and systems 2 4 (1989) 303\u2013314. 10.1007\/BF02551274","DOI":"10.1007\/BF02551274"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/019"},{"key":"e_1_3_3_1_8_2","unstructured":"Aditya\u00a0Nalgunda Ganesh. 2024. KAN-GPT: The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling. GitHub repository. https:\/\/github.com\/AdityaNG\/kan-gpt version 1.0.0 (released 2024-05-09)."},{"key":"e_1_3_3_1_9_2","unstructured":"GistNoesis. 2024. FusedFourierKAN: C++ & CUDA ops for fused Fourier Kolmogorov-Arnold Networks. GitHub repository. https:\/\/github.com\/GistNoesis\/FusedFourierKAN"},{"key":"e_1_3_3_1_10_2","first-page":"249","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/582034.582075"},{"key":"e_1_3_3_1_12_2","unstructured":"Chunyu Guo Lucheng Sun Shilong Li Zelong Yuan and Chao Wang. 2024. Physics-informed kolmogorov-arnold network with chebyshev polynomials for fluid mechanics. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.04516 (2024)."},{"key":"e_1_3_3_1_13_2","unstructured":"Kaggle. 2016. House Prices: Advanced Regression Techniques. Kaggle competition page. https:\/\/www.kaggle.com\/competitions\/house-prices-advanced-regression-techniques"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"A.\u00a0N. Kolmogorov. 1963. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. 55\u201359\u00a0pages. 10.1090\/trans2\/028\/04","DOI":"10.1090\/trans2\/028\/04"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. nature 521 7553 (2015) 436\u2013444.","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_1_16_2","unstructured":"Ziming Liu Yixuan Wang Sachin Vaidya Fabian Ruehle James Halverson Marin Solja\u010di\u0107 Thomas\u00a0Y Hou and Max Tegmark. 2024. Kan: Kolmogorov-arnold networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.19756 (2024)."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_3_1_18_2","volume-title":"cuBLAS Library User Guide","year":"2025","unstructured":"NVIDIA Corporation 2025. cuBLAS Library User Guide. NVIDIA Corporation, Santa Clara, CA. https:\/\/docs.nvidia.com\/cuda\/pdf\/CUBLAS_Library.pdf"},{"key":"e_1_3_3_1_19_2","volume-title":"CUDA Math API Reference Manual (release 12.9 ed.)","year":"2025","unstructured":"NVIDIA Corporation 2025. CUDA Math API Reference Manual (release 12.9 ed.). NVIDIA Corporation, Santa Clara, CA. https:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_Math_API.pdf Online documentation."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Cynthia Rudin. 2019. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature machine intelligence 1 5 (2019) 206\u2013215.","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"David\u00a0E. Rumelhart Geoffrey\u00a0E. Hinton and Ronald\u00a0J. Williams. 1986. Learning representations by back-propagating errors. Nature (Oct 1986) 533\u2013536. 10.1038\/323533a0","DOI":"10.1038\/323533a0"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Khemraj Shukla Juan\u00a0Diego Toscano Zhicheng Wang Zongren Zou and George\u00a0Em Karniadakis. 2024. A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks. Computer Methods in Applied Mechanics and Engineering 431 (2024) 117290.","DOI":"10.1016\/j.cma.2024.117290"},{"key":"e_1_3_3_1_23_2","unstructured":"Sidharth SS Keerthana AR and Anas KP. 2024. Chebyshev polynomial-based kolmogorov-arnold networks: An efficient architecture for nonlinear function approximation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.07200 (2024)."},{"key":"e_1_3_3_1_24_2","unstructured":"SynodicMonth. 2024. ChebyKAN: Kolmogorov-Arnold Networks using Chebyshev polynomials. GitHub repository. Retrieved 2025-08-13 from https:\/\/github.com\/SynodicMonth\/ChebyKAN commit 5f7efdd18e749bcc99481bd87dc90bdeafb920d8."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_3_1_26_2","unstructured":"Cassia Valentini-Botinhao. 2017. Noisy reverberant speech database for training speech enhancement algorithms and TTS models. Dataset. (2017). https:\/\/datashare.ed.ac.uk\/handle\/10283\/2826 Online dataset."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Y Wang J Sun J Bai C Anitescu MS Eshaghi X Zhuang T Rabczuk and Y Liu. 2025. A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov\u2013Arnold Networks. Computer Methods in Applied Mechanics and Engineering 433 (2025) 117518.","DOI":"10.1016\/j.cma.2024.117518"},{"key":"e_1_3_3_1_28_2","unstructured":"Pete Warden. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1804.03209 (2018)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Samuel Williams Andrew Waterman and David Patterson. 2009. Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52 4 (2009) 65\u201376.","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_3_1_30_2","unstructured":"Jinfeng Xu Zheyu Chen Jinze Li Shuo Yang Wei Wang Xiping Hu and Edith C-H Ngai. 2024. FourierKAN-GCF: Fourier Kolmogorov-Arnold Network\u2013An Effective and Efficient Feature Transformation for Graph Collaborative Filtering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01034 (2024)."},{"key":"e_1_3_3_1_31_2","unstructured":"Xingyi Yang and Xinchao Wang. 2024. Kolmogorov-arnold transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.10594 (2024)."},{"key":"e_1_3_3_1_32_2","unstructured":"Yu-Sen Yang Ling Guo and Xiaodan Ren. 2025. Multi-Resolution Training-Enhanced Kolmogorov-Arnold Networks for Multi-Scale PDE Problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.19888 (2025)."},{"key":"e_1_3_3_1_33_2","unstructured":"Runpeng Yu Weihao Yu and Xinchao Wang. 2024. Kan or mlp: A fairer comparison. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.16674 (2024)."},{"key":"e_1_3_3_1_34_2","unstructured":"Fan Zhang and Xin Zhang. 2024. Graphkan: Enhancing feature extraction with graph kolmogorov arnold networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.13597 (2024)."}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:43:18Z","timestamp":1782996198000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800535"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":33,"alternative-id":["10.1145\/3797905.3800535","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800535","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}