{"type":"ScholarlyArticle","title":"Efficient Localized Inference for Large Graphical Models","authors":[{"name":"Jinglin Chen","slug":"jinglin-chen","given":"Jinglin","family":"Chen","affiliation":"University of Illinois at Urbana-Champaign"},{"name":"Jian Peng","slug":"jian-peng","given":"Jian","family":"Peng","affiliation":"University of Illinois at Urbana-Champaign"},{"name":"Qiang Liu","slug":"qiang-liu","given":"Qiang","family":"Liu","affiliation":"University of Texas at Austin"}],"abstract":"We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property. Given a query variable and a large graphical model, we define a much smaller model in a local region around the query variable in the target model so that the marginal distribution of the query variable can be accurately approximated. We introduce two approximation error bounds based on the Dobrushin’s comparison theorem and apply our bounds to derive a greedy expansion algorithm that efficiently guides the selection of neighbor nodes for localized inference. We verify our theoretical bounds on various datasets and demonstrate that our localized inference algorithm can provide fast and accurate approximation for large graphical models.","doi":"10.24963/ijcai.2018/692","url":"https://ijcai.org/proceedings/2018/692","pdf":"https://ijcai.org/proceedings/2018/0692.pdf","markdown":"https://ijcai.org/proceedings/2018/692.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/692","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Uncertainty in AI","track":"Main track","number":692,"pages":{"first":4987,"last":4993},"keywords":["Uncertainty in AI: Approximate Probabilistic Inference","Uncertainty in AI: Graphical Models"],"videos":[],"references":[{"position":1,"raw":"[Chechetka and Guestrin, 2010] Anton Chechetka and Car- los Guestrin. Focused belief propagation for query- specific inference. In AISTATS, pages 89-96, 2010.","title":"Anton Chechetka and Carlos Guestrin. Focused belief propagation for queryspecific inference","authors":"Guestrin Chechetka","year":"2010","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Dechter, 2013] Rina Dechter. Reasoning with probabilis- tic and deterministic graphical models: Exact algorithms. Synthesis Lectures on Artificial Intelligence and Machine Learning, 7(3):1-191, 2013.","title":"Reasoning with probabilistic and deterministic graphical models: Exact algorithms","authors":"Rina Dechter","year":"2013","venue":"Synthesis Lectures on Artificial Intelligence and Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Föllmer, 1982] Hans Föllmer. A covariance estimate for gibbs measures. Journal of Functional Analysis, 46(3):387-395, 1982.","title":"A covariance estimate for gibbs measures","authors":"Hans Föllmer, Föllmer","year":"1982","venue":"Journal of Functional Analysis","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Heinemann and Globerson, 2014] Uri Heinemann and Amir Globerson. Inferning with high girth graphical models. In ICML, pages 1260-1268, 2014.","title":"Inferning with high girth graphical models","authors":"Globerson Heinemann, Uri Heinemann, Amir Globerson","year":"2014","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Koller and Friedman, 2009] Daphne Koller and Nir Fried- man. Probabilistic graphical models: principles and tech- niques. MIT press, 2009.","title":"Probabilistic graphical models: principles and techniques","authors":"Friedman Koller","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Rebeschini and van Handel, 2014] Patrick Rebeschini and Ramon van Handel. Comparison theorems for gibbs mea- sures. Journal of Statistical Physics, 157(2):234-281, 2014.","title":"Patrick Rebeschini and Ramon van Handel. Comparison theorems for gibbs measures","authors":"Van Rebeschini, Handel","year":"2014","venue":"Journal of Statistical Physics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Rebeschini et al., 2015] Patrick Rebeschini, Ramon Van Handel, et al. Can local particle filters beat the curse of dimensionality? The Annals of Applied Probability, 25(5):2809-2866, 2015.","title":"Can local particle filters beat the curse of dimensionality?","authors":"Patrick Rebeschini, Ramon Van Handel","year":"2015","venue":"The Annals of Applied Probability","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Shi et al., 2015] Tianlin Shi, Jacob Steinhardt, and Percy Liang. Learning where to sample in structured prediction. In AISTATS, 2015.","title":"Learning where to sample in structured prediction","authors":"Shi","year":"2015","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Wainwright et al., 2008] Martin J Wainwright, Michael I Jordan, et al. Graphical models, exponential families, and variational inference. Foundations and Trends R in Ma- chine Learning, 1(1-2):1-305, 2008.","title":"Graphical models, exponential families, and variational inference","authors":"J Martin, Michael I Wainwright, Jordan","year":"2008","venue":"Foundations and Trends R in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Wick and McCallum, 2011] Michael L Wick and Andrew McCallum. Query-aware mcmc. In Advances in Neural Information Processing Systems, pages 2564-2572, 2011.","title":"Query-aware mcmc","authors":"L Michael, Andrew Wick, Mccallum","year":"2011","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}