{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T18:19:34Z","timestamp":1760984374129,"version":"3.41.0"},"reference-count":24,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2012,1,11]],"date-time":"2012-01-11T00:00:00Z","timestamp":1326240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGOPS Oper. Syst. Rev."],"published-print":{"date-parts":[[2012,1,11]]},"abstract":"<jats:p>\n            In this paper, we address a pattern of diagnosis problems in which each of\n            <jats:italic>J<\/jats:italic>\n            entities produces the same\n            <jats:italic>K<\/jats:italic>\n            features, yet we are only informed of overall faults from the ensemble. Furthermore, we suspect that only certain entities and certain features are leading to the problem. The task, then, is to reliably identify which entities and which features are at fault. Such problems are particularly prevalent in the world of computer systems, in which a datacenter with hundreds of machines, each with the same performance counters, occasionally produces overall faults. In this paper, we present a means of using a constrained form of bilinear logistic regression for diagnosis in such problems. The bilinear treatment allows us to represent the scenarios with\n            <jats:italic>J+K<\/jats:italic>\n            instead of\n            <jats:italic>JK<\/jats:italic>\n            parameters, resulting in more easily interpretable results and far fewer false positives compared to treating the parameters independently. We develop statistical tests to determine which features and entities, if any, may be responsible for the labeled faults, and use false discovery rate (FDR) analysis to ensure that our values are meaningful. We show results in comparison to ordinary logistic regression (with L1 regularization) on two scenarios: a synthetic dataset based on a model of faults in a datacenter, and a real problem of finding problematic processes\/features based on user-reported hangs.\n          <\/jats:p>","DOI":"10.1145\/2094091.2094100","type":"journal-article","created":{"date-parts":[[2012,1,17]],"date-time":"2012-01-17T17:21:44Z","timestamp":1326820904000},"page":"31-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["BLR-D"],"prefix":"10.1145","volume":"45","author":[{"given":"Sumit","family":"Basu","sequence":"first","affiliation":[{"name":"Microsoft Research, Redmond, WA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Dunagan","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Duh","sequence":"additional","affiliation":[{"name":"NTT Labs, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiran-Kumar","family":"Muniswamy-Reddy","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,1,11]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/945445.945454"},{"volume-title":"New York: Springer","year":"2006","author":"Bishop C.M.","key":"e_1_2_1_2_1"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"volume-title":"Design and Implementation (OSDI)","year":"2006","author":"Chang F.","key":"e_1_2_1_4_1"},{"key":"e_1_2_1_5_1","unstructured":"Chen M. Kiciman E. Fratkin E. Fox A. and Brewer E. \"Pinpoint: Problem Determination in Large Dynamic Internet Services.\" In Dependable Sys. and Networks (DSN) 2002.   Chen M. Kiciman E. Fratkin E. Fox A. and Brewer E. \"Pinpoint: Problem Determination in Large Dynamic Internet Services.\" In Dependable Sys. and Networks (DSN) 2002."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1095810.1095821"},{"volume-title":"New York: Wiley","year":"1980","author":"Conover W. J.","key":"e_1_2_1_7_1"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294281"},{"key":"e_1_2_1_9_1","first-page":"1097","article-title":"Bilinear Discriminant Component Analysis","volume":"8","author":"Dyrholm M.","year":"2007","journal-title":"JMLR"},{"volume-title":"New York: Chapman & Hall","year":"1993","author":"Efron B.","key":"e_1_2_1_10_1"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/945445.945468"},{"key":"e_1_2_1_12_1","unstructured":"Friedman N. Goldszmidt M. and Wyner A. \"On the Application of the Bootstrap for Computing Confidence Features of Induced Bayesian Networks.\" In Proceedings of Artificial Intelligence and Statistics 1999.  Friedman N. Goldszmidt M. and Wyner A. \"On the Application of the Bootstrap for Computing Confidence Features of Induced Bayesian Networks.\" In Proceedings of Artificial Intelligence and Statistics 1999."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622859.1622869"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-007-0402-2"},{"volume-title":"Design and Implementation (OSDI)","year":"2006","author":"Kremenek T.","key":"e_1_2_1_15_1"},{"key":"e_1_2_1_16_1","unstructured":"Listgarten J. and Heckerman D. \"Determining the Number of Non-Spurious Arcs in a Learned DAG Model.\" In Proeedings of UAI 2007.  Listgarten J. and Heckerman D. \"Determining the Number of Non-Spurious Arcs in a Learned DAG Model.\" In Proeedings of UAI 2007."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294272"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1980-0572855-7"},{"key":"e_1_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Shwe M. Middleton B. Heckerman D. Henrion M. Horvitz E. Lehmann H. and Cooper G. \"Probabilistic Diagnosis Using a Reformulation of the INTERNIST-1\/QMR Knowledge Base.\" Methods of Information in Medicine (30): 241--255. 1991.  Shwe M. Middleton B. Heckerman D. Henrion M. Horvitz E. Lehmann H. and Cooper G. \"Probabilistic Diagnosis Using a Reformulation of the INTERNIST-1\/QMR Knowledge Base.\" Methods of Information in Medicine (30): 241--255. 1991.","DOI":"10.1055\/s-0038-1634846"},{"key":"e_1_2_1_20_1","unstructured":"Srinivasan S. Kandula S. Andrews C. and Zhou Y. \"Flashback: A Lightweight Extension for Rollback and Deterministic Replay for Software Debugging.\" In USENIX Annual Technical Conference 2004.   Srinivasan S. Kandula S. Andrews C. and Zhou Y. \"Flashback: A Lightweight Extension for Rollback and Deterministic Replay for Software Debugging.\" In USENIX Annual Technical Conference 2004."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1530509100"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294276"},{"key":"e_1_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Verbowski C. Kiciman E. Kumar A. Daniels B. Lu S. Lee J. Wang Y. and Roussev R. \"Flight Data Recorder: Monitoring Persistent-state Interactions to Improve Systems Management.\" In Operating Systems Design and Implementation (OSDI) 2006.   Verbowski C. Kiciman E. Kumar A. Daniels B. Lu S. Lee J. Wang Y. and Roussev R. \"Flight Data Recorder: Monitoring Persistent-state Interactions to Improve Systems Management.\" In Operating Systems Design and Implementation (OSDI) 2006.","DOI":"10.1145\/1140277.1140321"},{"volume-title":"Design and Implementation (OSDI)","year":"2004","author":"Wang H.","key":"e_1_2_1_24_1"}],"container-title":["ACM SIGOPS Operating Systems Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2094091.2094100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2094091.2094100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T09:48:41Z","timestamp":1750240121000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2094091.2094100"}},"subtitle":["applying bilinear logistic regression to factored diagnosis problems"],"short-title":[],"issued":{"date-parts":[[2012,1,11]]},"references-count":24,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,1,11]]}},"alternative-id":["10.1145\/2094091.2094100"],"URL":"https:\/\/doi.org\/10.1145\/2094091.2094100","relation":{},"ISSN":["0163-5980"],"issn-type":[{"type":"print","value":"0163-5980"}],"subject":[],"published":{"date-parts":[[2012,1,11]]},"assertion":[{"value":"2012-01-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}