{"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/scalable-population-synthesis-with-deep","title":"Scalable Population Synthesis with Deep Generative Modeling","arxiv_id":"1808.06910","date":"2018-08-21","proceeding":null,"authors":["Stanislav S. Borysov","Jeppe Rich","Francisco C. Pereira"],"abstract":"Population synthesis is concerned with the generation of synthetic yet\nrealistic representations of populations. It is a fundamental problem in the\nmodeling of transport where the synthetic populations of micro-agents represent\na key input to most agent-based models. In this paper, a new methodological\nframework for how to 'grow' pools of micro-agents is presented. The model\nframework adopts a deep generative modeling approach from machine learning\nbased on a Variational Autoencoder (VAE). Compared to the previous population\nsynthesis approaches, including Iterative Proportional Fitting (IPF), Gibbs\nsampling and traditional generative models such as Bayesian Networks or Hidden\nMarkov Models, the proposed method allows fitting the full joint distribution\nfor high dimensions. The proposed methodology is compared with a conventional\nGibbs sampler and a Bayesian Network by using a large-scale Danish trip diary.\nIt is shown that, while these two methods outperform the VAE in the\nlow-dimensional case, they both suffer from scalability issues when the number\nof modeled attributes increases. It is also shown that the Gibbs sampler\nessentially replicates the agents from the original sample when the required\nconditional distributions are estimated as frequency tables. In contrast, the\nVAE allows addressing the problem of sampling zeros by generating agents that\nare virtually different from those in the original data but have similar\nstatistical properties. The presented approach can support agent-based modeling\nat all levels by enabling richer synthetic populations with smaller zones and\nmore detailed individual characteristics.","url_abs":"http://arxiv.org/abs/1808.06910v2","url_pdf":"http://arxiv.org/pdf/1808.06910v2.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":"scalable-population-synthesis-with-deep","repo_url":"https://github.com/stasmix/popsynth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"scalable-population-synthesis-with-deep","repo_url":"https://github.com/fredshone/citychef","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"scalable-population-synthesis-with-deep","repo_url":"https://github.com/fredshone/pandamonia","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}