{"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/simple-distributed-and-accelerated","title":"Simple, Distributed, and Accelerated Probabilistic Programming","arxiv_id":"1811.02091","date":"2018-11-05","proceeding":"NeurIPS 2018 12","authors":["Dustin Tran","Matthew Hoffman","Dave Moore","Christopher Suter","Srinivas Vasudevan","Alexey Radul","Matthew Johnson","Rif A. Saurous"],"abstract":"We describe a simple, low-level approach for embedding probabilistic\nprogramming in a deep learning ecosystem. In particular, we distill\nprobabilistic programming down to a single abstraction---the random variable.\nOur lightweight implementation in TensorFlow enables numerous applications: a\nmodel-parallel variational auto-encoder (VAE) with 2nd-generation tensor\nprocessing units (TPUv2s); a data-parallel autoregressive model (Image\nTransformer) with TPUv2s; and multi-GPU No-U-Turn Sampler (NUTS). For both a\nstate-of-the-art VAE on 64x64 ImageNet and Image Transformer on 256x256\nCelebA-HQ, our approach achieves an optimal linear speedup from 1 to 256 TPUv2\nchips. With NUTS, we see a 100x speedup on GPUs over Stan and 37x over PyMC3.","url_abs":"http://arxiv.org/abs/1811.02091v2","url_pdf":"http://arxiv.org/pdf/1811.02091v2.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":"simple-distributed-and-accelerated","repo_url":"https://github.com/google/edward2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.02091","atlas_url":"https://app.syntology.ai/?focus=1811.02091","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}