{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/139258"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/139258","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Monkey: Platform-Agnostic Hybrid-Cloud Cluster Compute Orchestration Designed for AI/ML","abstract":"As AI/ML research progresses, the amount of compute needed to train and evaluate state-of-the-art AI algorithms consistently increases. With increasing needs for compute, researchers spend time designing distributed systems to scalably train and hyper-parameter optimize their latest model rather than focusing on their core research. We aim to build a fault-tolerant distributed system capable of cheaply and flexibly scheduling reproducible research training jobs on heterogeneous hybrid-cloud compute clusters including local machines and provider agnostic cloud machines. Our system focuses on ML researchers with two main goals, minimizing costs (using preemptible/spot-instances) and user friendliness. The system aims to require minimal user setup and configuration, allowing researchers to quickly get started training models. The Monkey System includes a web console and visualization dashboard to track, evaluate, and compare multiple jobs’ progress and results.","abstract_html":"As AI/ML research progresses, the amount of compute needed to train and evaluate state-of-the-art AI algorithms consistently increases. With increasing needs for compute, researchers spend time designing distributed systems to scalably train and hyper-parameter optimize their latest model rather than focusing on their core research. We aim to build a fault-tolerant distributed system capable of cheaply and flexibly scheduling reproducible research training jobs on heterogeneous hybrid-cloud compute clusters including local machines and provider agnostic cloud machines. Our system focuses on ML researchers with two main goals, minimizing costs (using preemptible/spot-instances) and user friendliness. The system aims to require minimal user setup and configuration, allowing researchers to quickly get started training models. The Monkey System includes a web console and visualization dashboard to track, evaluate, and compare multiple jobs’ progress and results.","abstract_has_math":false,"creators":["Lamp, Avery"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Agrawal, Pulkit"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-06","date_published":"2021-06","updated_at":"2026-07-22T22:21:30Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/139258","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Agrawal, Pulkit"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Lamp, Avery"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-01-14T14:59:56Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-01-14T14:59:56Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-06"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/139258"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As AI/ML research progresses, the amount of compute needed to train and evaluate state-of-the-art AI algorithms consistently increases. With increasing needs for compute, researchers spend time designing distributed systems to scalably train and hyper-parameter optimize their latest model rather than focusing on their core research. We aim to build a fault-tolerant distributed system capable of cheaply and flexibly scheduling reproducible research training jobs on heterogeneous hybrid-cloud compute clusters including local machines and provider agnostic cloud machines. Our system focuses on ML researchers with two main goals, minimizing costs (using preemptible/spot-instances) and user friendliness. The system aims to require minimal user setup and configuration, allowing researchers to quickly get started training models. The Monkey System includes a web console and visualization dashboard to track, evaluate, and compare multiple jobs’ progress and results."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Monkey: Platform-Agnostic Hybrid-Cloud Cluster Compute Orchestration Designed for AI/ML"]}]}],"canonical_facts":{"dc:contributor.advisor":["Agrawal, Pulkit"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Lamp, Avery"],"dc:date.accessioned":["2022-01-14T14:59:56Z"],"dc:date.available":["2022-01-14T14:59:56Z"],"dc:date.issued":["2021-06"],"dc:description.abstract":["As AI/ML research progresses, the amount of compute needed to train and evaluate state-of-the-art AI algorithms consistently increases. With increasing needs for compute, researchers spend time designing distributed systems to scalably train and hyper-parameter optimize their latest model rather than focusing on their core research. We aim to build a fault-tolerant distributed system capable of cheaply and flexibly scheduling reproducible research training jobs on heterogeneous hybrid-cloud compute clusters including local machines and provider agnostic cloud machines. Our system focuses on ML researchers with two main goals, minimizing costs (using preemptible/spot-instances) and user friendliness. The system aims to require minimal user setup and configuration, allowing researchers to quickly get started training models. The Monkey System includes a web console and visualization dashboard to track, evaluate, and compare multiple jobs’ progress and results."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/139258"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Monkey: Platform-Agnostic Hybrid-Cloud Cluster Compute Orchestration Designed for AI/ML"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:30Z"}