{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/improving-explorability-in-variational","title":"Improving Explorability in Variational Inference with Annealed Variational Objectives","arxiv_id":"1809.01818","date":"2018-09-06","proceeding":"NeurIPS 2018 12","authors":["Chin-wei Huang","Shawn Tan","Alexandre Lacoste","Aaron Courville"],"abstract":"Despite the advances in the representational capacity of approximate\ndistributions for variational inference, the optimization process can still\nlimit the density that is ultimately learned. We demonstrate the drawbacks of\nbiasing the true posterior to be unimodal, and introduce Annealed Variational\nObjectives (AVO) into the training of hierarchical variational methods.\nInspired by Annealed Importance Sampling, the proposed method facilitates\nlearning by incorporating energy tempering into the optimization objective. In\nour experiments, we demonstrate our method's robustness to deterministic warm\nup, and the benefits of encouraging exploration in the latent space.","url_abs":"http://arxiv.org/abs/1809.01818v3","url_pdf":"http://arxiv.org/pdf/1809.01818v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"improving-explorability-in-variational","repo_url":"https://github.com/alexey-pronkin/annealed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01818","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}