{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/113063"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/113063","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Optimization-based algebraic multigrid coarsening using reinforcement learning","abstract":"DSpace SAF Submission Ingestion Package generated from Vireo submission #16982 on 2022-01-12 at 12:46:07","abstract_html":"DSpace SAF Submission Ingestion Package generated from Vireo submission #16982 on 2022-01-12 at 12:46:07","abstract_has_math":false,"creators":["Taghibakhshi, Ali"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Mechanical Engineering","degree_department":null,"school":null,"contributors":["West, Mathew"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-01-12T21:46:52Z","date_published":"2022-01-12T21:46:52Z","updated_at":"2026-07-22T22:24:53Z","subjects":["Reinforcement Learning","Multigrid","Graph Neural Network"],"languages":["en"],"rights":["Copyright 2021 Ali Taghibakhshi"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/113063","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["West, Mathew"]},{"key":"dc:creator","label":"Author","values":["Taghibakhshi, Ali"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-01-12T21:46:52Z","2021-07-23","2021-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Reinforcement Learning","Multigrid","Graph Neural Network"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Ali Taghibakhshi"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/113063"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["DSpace SAF Submission Ingestion Package generated from Vireo submission #16982 on 2022-01-12 at 12:46:07","Made available in DSpace on 2022-01-12T21:46:52Z (GMT). No. of bitstreams: 2 TAGHIBAKHSHI-THESIS-2021.pdf: 6559251 bytes, checksum: af3175ac338ee20644297e486f89596b (MD5) LICENSE.txt: 4213 bytes, checksum: 3334b701e88358152710dadcb15801a5 (MD5) Previous issue date: 2021-07-23","Large sparse linear systems of equations are ubiquitous in science and engineering, such as those arising from discretizations of partial differential equations. Algebraic multigrid (AMG) methods are one of the most common methods of solving such linear systems, with an extensive body of underlying mathematical theory. A system of linear equations defines a graph on the set of unknowns and each level of a multigrid solver requires the selection of an appropriate coarse graph along with restriction and interpolation operators that map to and from the coarse representation. The efficiency of the multigrid solver depends critically on this selection and many selection methods have been developed over the years. Recently, it has been demonstrated that it is possible to directly learn the AMG interpolation and restriction operators, given a coarse graph selection. In this dissertation, we consider the complementary problem of learning to coarsen graphs for a multigrid solver. We study a method using a reinforcement learning (RL) agent based on two different neural network type; convolutional neural network (CNN) and graph neural networks (GNNs). The agent with CNN architecture is trained and tested on structured grids; however, the agent with GNN architecture can learn to perform graph coarsening on small training graphs and then be applied to unstructured large graphs. We demonstrate that this method can produce better coarse graphs than existing algorithms, even as the graph size increases and other properties of the graph are varied. We also propose an efficient inference procedure for performing graph coarsening that results in linear time complexity in graph size.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Ali Taghibakhshi, accepted the attached license on 2021-07-16 at 11:23.","The student, Ali Taghibakhshi, submitted this Thesis for approval on 2021-07-16 at 13:09.","This Thesis was approved for publication on 2021-07-23 at 09:30."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Optimization-based algebraic multigrid coarsening using reinforcement learning"]}]}],"canonical_facts":{"dc:contributor":["West, Mathew"],"dc:creator":["Taghibakhshi, Ali"],"dc:date":["2022-01-12T21:46:52Z","2021-07-23","2021-08"],"dc:description":["DSpace SAF Submission Ingestion Package generated from Vireo submission #16982 on 2022-01-12 at 12:46:07","Made available in DSpace on 2022-01-12T21:46:52Z (GMT). No. of bitstreams: 2 TAGHIBAKHSHI-THESIS-2021.pdf: 6559251 bytes, checksum: af3175ac338ee20644297e486f89596b (MD5) LICENSE.txt: 4213 bytes, checksum: 3334b701e88358152710dadcb15801a5 (MD5) Previous issue date: 2021-07-23","Large sparse linear systems of equations are ubiquitous in science and engineering, such as those arising from discretizations of partial differential equations. Algebraic multigrid (AMG) methods are one of the most common methods of solving such linear systems, with an extensive body of underlying mathematical theory. A system of linear equations defines a graph on the set of unknowns and each level of a multigrid solver requires the selection of an appropriate coarse graph along with restriction and interpolation operators that map to and from the coarse representation. The efficiency of the multigrid solver depends critically on this selection and many selection methods have been developed over the years. Recently, it has been demonstrated that it is possible to directly learn the AMG interpolation and restriction operators, given a coarse graph selection. In this dissertation, we consider the complementary problem of learning to coarsen graphs for a multigrid solver. We study a method using a reinforcement learning (RL) agent based on two different neural network type; convolutional neural network (CNN) and graph neural networks (GNNs). The agent with CNN architecture is trained and tested on structured grids; however, the agent with GNN architecture can learn to perform graph coarsening on small training graphs and then be applied to unstructured large graphs. We demonstrate that this method can produce better coarse graphs than existing algorithms, even as the graph size increases and other properties of the graph are varied. We also propose an efficient inference procedure for performing graph coarsening that results in linear time complexity in graph size.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Ali Taghibakhshi, accepted the attached license on 2021-07-16 at 11:23.","The student, Ali Taghibakhshi, submitted this Thesis for approval on 2021-07-16 at 13:09.","This Thesis was approved for publication on 2021-07-23 at 09:30."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/113063"],"dc:language":["en"],"dc:rights":["Copyright 2021 Ali Taghibakhshi"],"dc:subject":["Reinforcement Learning","Multigrid","Graph Neural Network"],"dc:title":["Optimization-based algebraic multigrid coarsening using reinforcement learning"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:53Z"}