Lucid Dreaming for Experience Replay<\/strong><\/p>\n\n\n\n Reinforcement-learning agents typically learn from a static buffer of past transitions. Lucid Dreaming for Experience Replay (LiDER)<\/em> \u201cre-dreams\u201d those memories under the agent\u2019s current policy, keeping only refreshed trajectories that improve on the originals. The result is higher sample-efficiency and better Atari scores\u2014all without altering the underlying off-policy algorithm.<\/p>\n\n\n\n Accountability & Legally-Aligned Fairness Metrics<\/strong><\/p>\n\n\n\n When datasets are small or highly imbalanced, popular evaluation metrics can become mathematically unstable, masking bias. One study (AISTATS 2025) pinpoints this sample-size-induced bias<\/em> and supplies reliability corrections. A companion effort (CIKM 2024) introduces the Objective Fairness Index (OFI), translating civil-rights doctrine into a robust numerical test. Together, these works give practitioners a principled toolkit for auditing models under real-world legal and data constraints.<\/p>\n\n\n\n AI & Machine Learning Lucid Dreaming for Experience Replay Reinforcement-learning agents typically learn from a static buffer of past transitions. Lucid Dreaming for Experience Replay (LiDER) \u201cre-dreams\u201d those memories under the agent\u2019s current policy, keeping only refreshed trajectories that improve on the originals. The result is higher sample-efficiency and better Atari scores\u2014all without altering the […]<\/p>\n","protected":false},"author":44146,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"categories":[],"tags":[],"university_category":[],"location":[],"organization":[],"_links":{"self":[{"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/pages\/1600"}],"collection":[{"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/users\/44146"}],"replies":[{"embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/comments?post=1600"}],"version-history":[{"count":8,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/pages\/1600\/revisions"}],"predecessor-version":[{"id":1842,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/pages\/1600\/revisions\/1842"}],"wp:attachment":[{"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/media?parent=1600"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/categories?post=1600"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/tags?post=1600"},{"taxonomy":"wsuwp_university_category","embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/university_category?post=1600"},{"taxonomy":"wsuwp_university_location","embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/location?post=1600"},{"taxonomy":"wsuwp_university_org","embeddable":true,"href":"https:\/\/labs.wsu.edu\/scads\/wp-json\/wp\/v2\/organization?post=1600"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\n\n\n
\n\n\n\nPapers<\/h2>\n\n\n\n
\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n\n\n\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n\n\n\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n\n\n\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
ScaWL: Scaling k-WL (Weisfeiler-Leman) Algorithms in Memory and Performance on Shared and Distributed-Memory Systems<\/a><\/strong>, ACM TACO<\/em> (accepted 2024).
Abstract<\/a> | Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
Direction-Optimizing Label Propagation Framework for Structure Detection in Graphs: Design, Implementation, and Experimental Analysis<\/a><\/strong>, ACM Journal of Experimental Algorithmics<\/em> 27 (1.12), 1\u201331 (2022).
Abstract<\/a> | Paper in PDF<\/a><\/li>\n\n\n\n
Direction-Optimizing Label Propagation and Its Application to Community Detection<\/a><\/strong>, Computing Frontiers<\/em> 2020.
Abstract<\/a> | Paper in PDF<\/a><\/li>\n\n\n\n
Distributed Direction-Optimizing Label Propagation for Community Detection<\/a><\/strong>, IEEE HPEC 2019 (Graph Challenge Innovation Award).
Abstract<\/a> | Paper in PDF<\/a><\/li>\n\n\n\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n\n\n\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n\n\n\n
Abstract<\/a> Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
Cast to Vote: A Socio-technical Network Analysis of an Election Smartphone Application, Digital Government: Research and Practice<\/em> 3 (1), <\/a><\/strong>Article 3, 117 (2022).
<\/a><\/strong>Abstract<\/a> | Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
High-Order Line Graphs of Non-Uniform Hypergraphs: Algorithms, Applications, and Experimental Analysis<\/a><\/strong>, IEEE IPDPS 2022.
Abstract<\/a> | Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
NWHy: A Framework for Hypergraph Analytics\u2014Representations, Data Structures, and Algorithms<\/a><\/strong>, IEEE IPDPS Workshops 2022.
Abstract<\/a> | Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
Parallel Algorithms for Efficient Computation of High-Order Line Graphs of Hypergraphs<\/a><\/strong>, IEEE HiPC 2021.
Abstract<\/a> | Paper in PDF<\/a><\/li>\n<\/ul>\n\n\n\n\n
Exploring MPI Communication Models for Graph Applications Using Graph Matching as a Case Study<\/a><\/strong>, IEEE IPDPS 2019.
Abstract<\/a> | Paper in PDF<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"