{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:50Z","timestamp":1776931250302,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767543","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"1800-1807","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fast Linear Solvers via AI-Tuned Markov Chain Monte Carlo-based Matrix Inversion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4946-2974","authenticated-orcid":false,"given":"Anton","family":"Lebedev","sequence":"first","affiliation":[{"name":"STFC Hartree Centre, Warrington, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3465-6094","authenticated-orcid":false,"given":"Won Kyung","family":"Lee","sequence":"additional","affiliation":[{"name":"STFC Hartree Centre, Warrington, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1642-1891","authenticated-orcid":false,"given":"Soumyadip","family":"Ghosh","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1727-9461","authenticated-orcid":false,"given":"Olha I.","family":"Yaman","sequence":"additional","affiliation":[{"name":"STFC Hartree Centre, Warrington, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4614-6422","authenticated-orcid":false,"given":"Vassilis","family":"Kalantzis","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3672-0865","authenticated-orcid":false,"given":"Yingdong","family":"Lu","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8260-0231","authenticated-orcid":false,"given":"Tomasz","family":"Nowicki","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6942-7158","authenticated-orcid":false,"given":"Shashanka","family":"Ubaru","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6350-0238","authenticated-orcid":false,"given":"Lior","family":"Horesh","sequence":"additional","affiliation":[{"name":"IBM Thomas J. Watson Research Center, Yorktown Heights, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4889-1207","authenticated-orcid":false,"given":"Vassil","family":"Alexandrov","sequence":"additional","affiliation":[{"name":"STFC Hartree Centre, Warrington, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Peter\u00a0W Battaglia Jessica\u00a0B Hamrick Victor Bapst Alvaro Sanchez-Gonzalez Vinicius Zambaldi Mateusz Malinowski Andrea Tacchetti David Raposo Adam Santoro Ryan Faulkner et\u00a0al. 2018. Relational inductive biases deep learning and graph networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.01261 (2018)."},{"key":"e_1_3_3_2_3_2","unstructured":"James Bergstra R\u00e9mi Bardenet Yoshua Bengio and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems 24 (2011)."},{"key":"e_1_3_3_2_4_2","volume-title":"International Conference on Learning Representations","author":"Brody Shaked","year":"2022","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2022. How Attentive are Graph Attention Networks?. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=F72ximsx7C1"},{"key":"e_1_3_3_2_5_2","unstructured":"David Buterez Jon\u00a0Paul Janet Steven\u00a0J Kiddle Dino Oglic and Pietro Li\u00f2. 2022. Graph neural networks with adaptive readouts. Advances in Neural Information Processing Systems 35 (2022) 19746\u201319758."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0H Byrd Peihuang Lu Jorge Nocedal and Ciyou Zhu. 1995. A limited memory algorithm for bound constrained optimization. SIAM Journal on Scientific Computing 16 5 (1995) 1190\u20131208.","DOI":"10.1137\/0916069"},{"key":"e_1_3_3_2_7_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Chen Jie","year":"2025","unstructured":"Jie Chen. 2025. Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Tkkrm3pA35"},{"key":"e_1_3_3_2_8_2","unstructured":"Gabriele Corso Luca Cavalleri Dominique Beaini Pietro Li\u00f2 and Petar Veli\u010dkovi\u0107. 2020. Principal neighbourhood aggregation for graph nets. Advances in Neural Information Processing Systems 33 (2020) 13260\u201313271."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Geoffrey Dillon Vassilis Kalantzis Yuanzhe Xi and Yousef Saad. 2018. A hierarchical low rank Schur complement preconditioner for indefinite linear systems. SIAM Journal on Scientific Computing 40 4 (2018) A2234\u2013A2252.","DOI":"10.1137\/17M1143320"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Soumyadip Ghosh Lior Horesh Vassilis Kalantzis Yingdong Lu and Tomasz Nowicki. 2025. Regenerative Ulam-von Neumann Algorithm: An Innovative Markov chain Monte Carlo Method for Matrix Inversion. SIAM Journal on Matrix Analysis and Applications (to appear) (2025).","DOI":"10.1137\/24M1685547"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Marcus\u00a0J Grote and Thomas Huckle. 1997. Parallel preconditioning with sparse approximate inverses. SIAM Journal on Scientific Computing 18 3 (1997) 838\u2013853.","DOI":"10.1137\/S1064827594276552"},{"key":"e_1_3_3_2_12_2","volume-title":"International Conference on Learning Representations","author":"Hu* Weihua","year":"2020","unstructured":"Weihua Hu*, Bowen Liu*, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, and Jure Leskovec. 2020. Strategies for Pre-training Graph Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HJlWWJSFDH"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Vassilis Kalantzis. 2020. A domain decomposition Rayleigh\u2013Ritz algorithm for symmetric generalized eigenvalue problems. SIAM Journal on Scientific Computing 42 6 (2020) C410\u2013C435.","DOI":"10.1137\/19M1280004"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Vassilis Kalantzis and Lior Horesh. 2023. Enhanced algebraic substructuring for symmetric generalized eigenvalue problems. Numerical Linear Algebra with Applications 30 2 (2023) e2473.","DOI":"10.1002\/nla.2473"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Vassilis Kalantzis Yuanzhe Xi and Lior Horesh. 2021. Fast randomized non-Hermitian eigensolvers based on rational filtering and matrix partitioning. SIAM Journal on Scientific Computing 43 5 (2021) S791\u2013S815.","DOI":"10.1137\/20M1349217"},{"key":"e_1_3_3_2_16_2","first-page":"1","volume-title":"ICLR: International Conference on Learning Representations","author":"Kingma Diederik\u00a0P","year":"2015","unstructured":"Diederik\u00a0P Kingma and Jimmy\u00a0Lei Ba. 2015. Adam: A method for stochastic gradient descent. In ICLR: International Conference on Learning Representations. 1\u201315."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA.2018.00014"},{"key":"e_1_3_3_2_18_2","unstructured":"Liam Li Kevin Jamieson Afshin Rostamizadeh Ekaterina Gonina Jonathan Ben-Tzur Moritz Hardt Benjamin Recht and Ameet Talwalkar. 2020. A system for massively parallel hyperparameter tuning. Proceedings of Machine Learning and Systems 2 (2020) 230\u2013246."},{"key":"e_1_3_3_2_19_2","first-page":"19425","volume-title":"International Conference on Machine Learning","author":"Li Yichen","year":"2023","unstructured":"Yichen Li, Peter\u00a0Yichen Chen, Tao Du, and Wojciech Matusik. 2023. Learning preconditioners for conjugate gradient PDE solvers. In International Conference on Machine Learning. PMLR, 19425\u201319439."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Haitao Liu Yew-Soon Ong Xiaobo Shen and Jianfei Cai. 2020. When Gaussian process meets big data: A review of scalable GPs. IEEE Transactions on Neural Networks and Learning Systems 31 11 (2020) 4405\u20134423.","DOI":"10.1109\/TNNLS.2019.2957109"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Jian Luo Jie Wang Hong Wang Zijie Geng Hanzhu Chen Yufei Kuang et\u00a0al. 2024. Neural Krylov iteration for accelerating linear system solving. Advances in Neural Information Processing Systems 37 (2024) 128636\u2013128667.","DOI":"10.52202\/079017-4086"},{"key":"e_1_3_3_2_22_2","unstructured":"Erich Merrill Alan Fern Xiaoli Fern and Nima Dolatnia. 2021. An empirical study of bayesian optimization: Acquisition versus partition. Journal of Machine Learning Research 22 4 (2021) 1\u201325."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Jonas Mockus. 1994. Application of Bayesian approach to numerical methods of global and stochastic optimization. Journal of Global Optimization 4 4 (1994) 347\u2013365.","DOI":"10.1007\/BF01099263"},{"key":"e_1_3_3_2_24_2","unstructured":"Jonas Mockus. 1998. The application of Bayesian methods for seeking the extremum. Towards Global Optimization 2 (1998) 117."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Yousef Saad. 1994. ILUT: A dual threshold incomplete LU factorization. Numerical linear algebra with applications 1 4 (1994) 387\u2013402.","DOI":"10.1002\/nla.1680010405"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA54577.2021.00011"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/214"},{"key":"e_1_3_3_2_30_2","unstructured":"Niranjan Srinivas Andreas Krause Sham\u00a0M Kakade and Matthias Seeger. 2009. Gaussian process optimization in the bandit setting: No regret and experimental design. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/0912.3995 (2009)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"J Stra\u00dfburg and Vassil\u00a0N Alexandrov. 2013. A Monte Carlo approach to sparse approximate inverse matrix computations. Procedia Computer Science 18 (2013) 2307\u20132316.","DOI":"10.1016\/j.procs.2013.05.402"},{"key":"e_1_3_3_2_32_2","unstructured":"Vladislav Trifonov Alexander Rudikov Oleg Iliev Yuri\u00a0M Laevsky Ivan Oseledets and Ekaterina Muravleva. 2024. Learning from linear algebra: A graph neural network approach to preconditioner design for conjugate gradient solvers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.15557 (2024)."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Yue Wang Yongbin Sun Ziwei Liu Sanjay\u00a0E Sarma Michael\u00a0M Bronstein and Justin\u00a0M Solomon. 2019. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (TOG) 38 5 (2019) 1\u201312.","DOI":"10.1145\/3326362"},{"key":"e_1_3_3_2_34_2","first-page":"370","volume-title":"Artificial intelligence and statistics","author":"Wilson Andrew\u00a0Gordon","year":"2016","unstructured":"Andrew\u00a0Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, and Eric\u00a0P Xing. 2016. Deep kernel learning. In Artificial intelligence and statistics. PMLR, 370\u2013378."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Edwin\u00a0B Wilson. 1927. Probable inference the law of succession and statistical inference. J. Amer. Statist. Assoc. 22 158 (1927) 209\u2013212.","DOI":"10.1080\/01621459.1927.10502953"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Tianshi Xu Vassilis Kalantzis Ruipeng Li Yuanzhe Xi Geoffrey Dillon and Yousef Saad. 2022. parGeMSLR: A parallel multilevel Schur complement low-rank preconditioning and solution package for general sparse matrices. Parallel Comput. 113 (2022) 102956.","DOI":"10.1016\/j.parco.2022.102956"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:31:30Z","timestamp":1767987090000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":35,"alternative-id":["10.1145\/3731599.3767543","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767543","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}