@inproceedings{HAR-20,
  title={Attention for Inference Compilation},
  author={Harvey, W and Munk, A and Baydin, AG and Bergholm, A and Wood, F},
  booktitle={The second International Conference on Probabilistic Programming (PROBPROG)},
  year={2020},
  archiveprefix = {arXiv},
  eprint = {1910.11961},
  support = {D3M,LwLL},
  url_Paper={https://arxiv.org/pdf/1910.11961.pdf},
  url_ArXiv={https://arxiv.org/abs/1910.11961},
  url_Poster={https://github.com/plai-group/bibliography/blob/master/presentations_posters/PROBPROG2020_HAR.pdf},
  abstract = {We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural networks to approximate a posterior distribution over latent variables in a probabilistic program. A challenge with existing IC network architectures is that they can fail to model long-range dependencies between latent variables. To address this, we introduce an attention mechanism that attends to the most salient variables previously sampled in the execution of a probabilistic program. We demonstrate that the addition of attention allows the proposal distributions to better match the true posterior, enhancing inference about latent variables in simulators.},
}

{"_id":"cwscrCmvwEXJ2b6d3","bibbaseid":"harvey-munk-baydin-bergholm-wood-attentionforinferencecompilation-2020","authorIDs":[],"author_short":["Harvey, W","Munk, A","Baydin, A.","Bergholm, A","Wood, F"],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Attention for Inference Compilation","author":[{"propositions":[],"lastnames":["Harvey"],"firstnames":["W"],"suffixes":[]},{"propositions":[],"lastnames":["Munk"],"firstnames":["A"],"suffixes":[]},{"propositions":[],"lastnames":["Baydin"],"firstnames":["AG"],"suffixes":[]},{"propositions":[],"lastnames":["Bergholm"],"firstnames":["A"],"suffixes":[]},{"propositions":[],"lastnames":["Wood"],"firstnames":["F"],"suffixes":[]}],"booktitle":"The second International Conference on Probabilistic Programming (PROBPROG)","year":"2020","archiveprefix":"arXiv","eprint":"1910.11961","support":"D3M,LwLL","url_paper":"https://arxiv.org/pdf/1910.11961.pdf","url_arxiv":"https://arxiv.org/abs/1910.11961","url_poster":"https://github.com/plai-group/bibliography/blob/master/presentations_posters/PROBPROG2020_HAR.pdf","abstract":"We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural networks to approximate a posterior distribution over latent variables in a probabilistic program. A challenge with existing IC network architectures is that they can fail to model long-range dependencies between latent variables. To address this, we introduce an attention mechanism that attends to the most salient variables previously sampled in the execution of a probabilistic program. We demonstrate that the addition of attention allows the proposal distributions to better match the true posterior, enhancing inference about latent variables in simulators.","bibtex":"@inproceedings{HAR-20,\n title={Attention for Inference Compilation},\n author={Harvey, W and Munk, A and Baydin, AG and Bergholm, A and Wood, F},\n booktitle={The second International Conference on Probabilistic Programming (PROBPROG)},\n year={2020},\n archiveprefix = {arXiv},\n eprint = {1910.11961},\n support = {D3M,LwLL},\n url_Paper={https://arxiv.org/pdf/1910.11961.pdf},\n url_ArXiv={https://arxiv.org/abs/1910.11961},\n url_Poster={https://github.com/plai-group/bibliography/blob/master/presentations_posters/PROBPROG2020_HAR.pdf},\n abstract = {We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural networks to approximate a posterior distribution over latent variables in a probabilistic program. A challenge with existing IC network architectures is that they can fail to model long-range dependencies between latent variables. To address this, we introduce an attention mechanism that attends to the most salient variables previously sampled in the execution of a probabilistic program. We demonstrate that the addition of attention allows the proposal distributions to better match the true posterior, enhancing inference about latent variables in simulators.},\n}\n\n","author_short":["Harvey, W","Munk, A","Baydin, A.","Bergholm, A","Wood, F"],"key":"HAR-20","id":"HAR-20","bibbaseid":"harvey-munk-baydin-bergholm-wood-attentionforinferencecompilation-2020","role":"author","urls":{" paper":"https://arxiv.org/pdf/1910.11961.pdf"," arxiv":"https://arxiv.org/abs/1910.11961"," poster":"https://github.com/plai-group/bibliography/blob/master/presentations_posters/PROBPROG2020_HAR.pdf"},"metadata":{"authorlinks":{}},"downloads":10},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/plai-group/bibliography/master/group_publications.bib","creationDate":"2020-01-28T23:30:32.212Z","downloads":10,"keywords":[],"search_terms":["attention","inference","compilation","harvey","munk","baydin","bergholm","wood"],"title":"Attention for Inference Compilation","year":2020,"dataSources":["7avRLRrz2ifJGMKcD","BKH7YtW7K7WNMA3cj","wyN5DxtoT6AQuiXnm"]}