Advances in approximate inference: combining VI and MCMC and improving on Stein discrepancyJan 1, 2022·Wenbo Gong· 0 min read PDF Cite Source DocumentTypeThesisPublicationPhD thesis, University of CambridgeLast updated on Jan 1, 2022 AuthorsWenbo GongSenior ResearcherSenior Researcher at Microsoft Research Cambridge working on learning dynamics and optimization for foundation models, with prior work on causality and approximate inference. ← Understanding causality with large language models: Feasibility and opportunities Jan 1, 2023Simultaneous missing value imputation and structure learning with groups Jan 1, 2022 →
·
0 min read