{"id":41501,"date":"2026-01-30T12:31:08","date_gmt":"2026-01-30T17:31:08","guid":{"rendered":"https:\/\/www.bu.edu\/hic\/?p=41501"},"modified":"2026-02-06T13:17:09","modified_gmt":"2026-02-06T18:17:09","slug":"41501","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/hic\/2026\/01\/30\/41501\/","title":{"rendered":"Boston University\u2019s Sarah Milligan Launches First Comprehensive R Package Bringing Variational Autoencoders to Tabular Data"},"content":{"rendered":"<p><em><span style=\"font-weight: 400;\">By Hariri Institute Staff<\/span><\/em><\/p>\n<figure id=\"attachment_37930\" aria-describedby=\"caption-attachment-37930\" style=\"width: 289px\" class=\"wp-caption alignleft\"><a href=\"https:\/\/www.bu.edu\/hic\/2025\/11\/07\/advances-in-synthetic-data-generation-for-public-health-research\/\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" src=\"\/hic\/files\/2025\/04\/Sarah-Milligan-_-headshot-509x636.jpeg\" alt=\"\" width=\"279\" height=\"349\" class=\"wp-image-37930\" \/><\/a><figcaption id=\"caption-attachment-37930\" class=\"wp-caption-text\">Sarah Milligan, a 2025 Hariri Institute Graduate Student Fellow and PhD candidate in Biostatistics at the BU School of Public Health<\/figcaption><\/figure>\n<p><span style=\"font-weight: 400;\"><a href=\"https:\/\/www.bu.edu\/hic\/2025\/11\/07\/advances-in-synthetic-data-generation-for-public-health-research\/\" target=\"_blank\" rel=\"noopener\">Sarah Milligan<\/a>, a 2025 Hariri Institute Graduate Student Fellow and PhD candidate in Biostatistics at the BU <a href=\"https:\/\/www.bu.edu\/sph\/\" target=\"_blank\" rel=\"noopener\">School of Public Health<\/a>, has developed a groundbreaking R package that brings Variational Autoencoders (VAEs) to tabular data, the first comprehensive tool of its kind available in the R programming language.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">VAEs are a type of machine learning model typically used for images or text, but Milligan\u2019s work adapts them to structured data found in spreadsheets or databases, such as medical records. The package allows researchers to implement VAEs on tabular data to uncover patterns within the data and generate synthetic datasets, making it easier to share and analyze data securely while accelerating research.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The package, AutoTab, provides flexible regularization options, supports \u03b2-VAE training via warm-up or cyclical annealing, introduces a new method for weighting distributional types within the ELBO, and offers numerous additional customization features, all achievable in as few as three lines of code.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">By combining biostatistics with cutting-edge machine learning, this open-source tool introduces new statistical methods to the field and supports reproducible research. It is now available on t<\/span>he Comprehensive R Archive Network (CRAN)<span style=\"font-weight: 400;\">, opening these powerful capabilities to R users, data scientists, and researchers across disciplines.<\/span><\/p>\n<p>Access the package here: <a href=\"https:\/\/cran.r-project.org\/web\/packages\/autotab\/index.html\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">https:\/\/cran.r-project.org\/web\/packages\/autotab\/index.html<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>By Hariri Institute Staff Sarah Milligan, a 2025 Hariri Institute Graduate Student Fellow and PhD candidate in Biostatistics at the BU School of Public Health, has developed a groundbreaking R package that brings Variational Autoencoders (VAEs) to tabular data, the first comprehensive tool of its kind available in the R programming language. VAEs are a [&hellip;]<\/p>\n","protected":false},"author":22836,"featured_media":41504,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[11832,1],"tags":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts\/41501"}],"collection":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/users\/22836"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/comments?post=41501"}],"version-history":[{"count":2,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts\/41501\/revisions"}],"predecessor-version":[{"id":41506,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/posts\/41501\/revisions\/41506"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/media\/41504"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/media?parent=41501"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/categories?post=41501"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/hic\/wp-json\/wp\/v2\/tags?post=41501"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}