@inproceedings{BRE-20,
  author = {{Brekelmans}, Rob and {Masrani}, Vaden and {Wood}, Frank and {Ver Steeg}, Greg and {Galstyan}, Aram},
  title = {All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference},
  booktitle={Thirty-seventh International Conference on Machine Learning (ICML 2020)},
  keywords = {Computer Science - Machine Learning, Statistics - Machine Learning},
  year = 2020,
  month = jul,
  eid = {arXiv:2007.00642},
  archivePrefix = {arXiv},
  eprint = {2007.00642},
  url_Link = {https://proceedings.icml.cc/book/2020/hash/12311d05c9aa67765703984239511212},
  url_Paper={https://proceedings.icml.cc/static/paper_files/icml/2020/2826-Paper.pdf},
  url_ArXiv={https://arxiv.org/abs/2007.00642},
  support = {D3M},
  abstract={The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and generalize the ubiquitous Evidence Lower Bound (ELBO). However, the tightness of TVO bounds was not previously known, an expensive grid search was used to choose a "schedule" of intermediate distributions, and model learning suffered with ostensibly tighter bounds. In this work, we propose an exponential family interpretation of the geometric mixture curve underlying the TVO and various path sampling methods, which allows us to characterize the gap in TVO likelihood bounds as a sum of KL divergences. We propose to choose intermediate distributions using equal spacing in the moment parameters of our exponential family, which matches grid search performance and allows the schedule to adaptively update over the course of training. Finally, we derive a doubly reparameterized gradient estimator which improves model learning and allows the TVO to benefit from more refined bounds. To further contextualize our contributions, we provide a unified framework for understanding thermodynamic integration and the TVO using Taylor series remainders.}
  }

%@unpublished{WOO-20,
%  author = {{Wood}, Frank and {Warrington}, Andrew and {Naderiparizi}, Saeid and {Weilbach}, Christian and {Masrani}, Vaden and {Harvey}, William and {Scibior}, Adam and {Beronov}, Boyan and {Nasseri}, Ali},
%  title = {Planning as Inference in Epidemiological Models},
%  journal = {arXiv e-prints},
%  keywords = {Quantitative Biology - Populations and Evolution, Computer Science - Machine Learning, Statistics - Machine Learning},
%  year = {2020},
%  eid = {arXiv:2003.13221},
%  archivePrefix = {arXiv},
%  eprint = {2003.13221},
%  support = {D3M,COVID,ETALUMIS},
%  url_ArXiv={https://arxiv.org/abs/2003.13221},
%  url_Paper={https://arxiv.org/pdf/2003.13221.pdf},
%  abstract={In this work we demonstrate how existing software tools can be used to automate parts of infectious disease-control policy-making via performing inference in existing epidemiological dynamics models. The kind of inference tasks undertaken include computing, for planning purposes, the posterior distribution over putatively controllable, via direct policy-making choices, simulation model parameters that give rise to acceptable disease progression outcomes. Neither the full capabilities of such inference automation software tools nor their utility for planning is widely disseminated at the current time. Timely gains in understanding about these tools and how they can be used may lead to more fine-grained and less economically damaging policy prescriptions, particularly during the current COVID-19 pandemic.}
%}

{"_id":"dvSB3x7PnzfFPGiTx","bibbaseid":"brekelmans-masrani-wood-versteeg-galstyan-allintheexponentialfamilybregmandualityinthermodynamicvariationalinference-2020","authorIDs":[],"author_short":["Brekelmans, R.","Masrani, V.","Wood, F.","Ver Steeg, G.","Galstyan, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Brekelmans"],"firstnames":["Rob"],"suffixes":[]},{"propositions":[],"lastnames":["Masrani"],"firstnames":["Vaden"],"suffixes":[]},{"propositions":[],"lastnames":["Wood"],"firstnames":["Frank"],"suffixes":[]},{"propositions":[],"lastnames":["Ver Steeg"],"firstnames":["Greg"],"suffixes":[]},{"propositions":[],"lastnames":["Galstyan"],"firstnames":["Aram"],"suffixes":[]}],"title":"All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference","booktitle":"Thirty-seventh International Conference on Machine Learning (ICML 2020)","keywords":"Computer Science - Machine Learning, Statistics - Machine Learning","year":"2020","month":"July","eid":"arXiv:2007.00642","archiveprefix":"arXiv","eprint":"2007.00642","url_link":"https://proceedings.icml.cc/book/2020/hash/12311d05c9aa67765703984239511212","url_paper":"https://proceedings.icml.cc/static/paper_files/icml/2020/2826-Paper.pdf","url_arxiv":"https://arxiv.org/abs/2007.00642","support":"D3M","abstract":"The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and generalize the ubiquitous Evidence Lower Bound (ELBO). However, the tightness of TVO bounds was not previously known, an expensive grid search was used to choose a \"schedule\" of intermediate distributions, and model learning suffered with ostensibly tighter bounds. In this work, we propose an exponential family interpretation of the geometric mixture curve underlying the TVO and various path sampling methods, which allows us to characterize the gap in TVO likelihood bounds as a sum of KL divergences. We propose to choose intermediate distributions using equal spacing in the moment parameters of our exponential family, which matches grid search performance and allows the schedule to adaptively update over the course of training. Finally, we derive a doubly reparameterized gradient estimator which improves model learning and allows the TVO to benefit from more refined bounds. To further contextualize our contributions, we provide a unified framework for understanding thermodynamic integration and the TVO using Taylor series remainders.","bibtex":"@inproceedings{BRE-20,\n author = {{Brekelmans}, Rob and {Masrani}, Vaden and {Wood}, Frank and {Ver Steeg}, Greg and {Galstyan}, Aram},\n title = {All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference},\n booktitle={Thirty-seventh International Conference on Machine Learning (ICML 2020)},\n keywords = {Computer Science - Machine Learning, Statistics - Machine Learning},\n year = 2020,\n month = jul,\n eid = {arXiv:2007.00642},\n archivePrefix = {arXiv},\n eprint = {2007.00642},\n url_Link = {https://proceedings.icml.cc/book/2020/hash/12311d05c9aa67765703984239511212},\n url_Paper={https://proceedings.icml.cc/static/paper_files/icml/2020/2826-Paper.pdf},\n url_ArXiv={https://arxiv.org/abs/2007.00642},\n support = {D3M},\n abstract={The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and generalize the ubiquitous Evidence Lower Bound (ELBO). However, the tightness of TVO bounds was not previously known, an expensive grid search was used to choose a \"schedule\" of intermediate distributions, and model learning suffered with ostensibly tighter bounds. In this work, we propose an exponential family interpretation of the geometric mixture curve underlying the TVO and various path sampling methods, which allows us to characterize the gap in TVO likelihood bounds as a sum of KL divergences. We propose to choose intermediate distributions using equal spacing in the moment parameters of our exponential family, which matches grid search performance and allows the schedule to adaptively update over the course of training. Finally, we derive a doubly reparameterized gradient estimator which improves model learning and allows the TVO to benefit from more refined bounds. To further contextualize our contributions, we provide a unified framework for understanding thermodynamic integration and the TVO using Taylor series remainders.}\n }\n\n%@unpublished{WOO-20,\n% author = {{Wood}, Frank and {Warrington}, Andrew and {Naderiparizi}, Saeid and {Weilbach}, Christian and {Masrani}, Vaden and {Harvey}, William and {Scibior}, Adam and {Beronov}, Boyan and {Nasseri}, Ali},\n% title = {Planning as Inference in Epidemiological Models},\n% journal = {arXiv e-prints},\n% keywords = {Quantitative Biology - Populations and Evolution, Computer Science - Machine Learning, Statistics - Machine Learning},\n% year = {2020},\n% eid = {arXiv:2003.13221},\n% archivePrefix = {arXiv},\n% eprint = {2003.13221},\n% support = {D3M,COVID,ETALUMIS},\n% url_ArXiv={https://arxiv.org/abs/2003.13221},\n% url_Paper={https://arxiv.org/pdf/2003.13221.pdf},\n% abstract={In this work we demonstrate how existing software tools can be used to automate parts of infectious disease-control policy-making via performing inference in existing epidemiological dynamics models. The kind of inference tasks undertaken include computing, for planning purposes, the posterior distribution over putatively controllable, via direct policy-making choices, simulation model parameters that give rise to acceptable disease progression outcomes. Neither the full capabilities of such inference automation software tools nor their utility for planning is widely disseminated at the current time. Timely gains in understanding about these tools and how they can be used may lead to more fine-grained and less economically damaging policy prescriptions, particularly during the current COVID-19 pandemic.}\n%}\n\n","author_short":["Brekelmans, R.","Masrani, V.","Wood, F.","Ver Steeg, G.","Galstyan, A."],"key":"BRE-20","id":"BRE-20","bibbaseid":"brekelmans-masrani-wood-versteeg-galstyan-allintheexponentialfamilybregmandualityinthermodynamicvariationalinference-2020","role":"author","urls":{" link":"https://proceedings.icml.cc/book/2020/hash/12311d05c9aa67765703984239511212"," paper":"https://proceedings.icml.cc/static/paper_files/icml/2020/2826-Paper.pdf"," arxiv":"https://arxiv.org/abs/2007.00642"},"keyword":["Computer Science - Machine Learning","Statistics - Machine Learning"],"metadata":{"authorlinks":{}},"downloads":5},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/plai-group/bibliography/master/group_publications.bib","creationDate":"2020-07-03T20:46:42.925Z","downloads":5,"keywords":["computer science - machine learning","statistics - machine learning"],"search_terms":["exponential","family","bregman","duality","thermodynamic","variational","inference","brekelmans","masrani","wood","ver steeg","galstyan"],"title":"All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference","year":2020,"dataSources":["7avRLRrz2ifJGMKcD","X69gAvDa3qySitobN","AurbPYNYbHmtrsQ7q","BKH7YtW7K7WNMA3cj","WKAs5u54exPpcdrJw","wyN5DxtoT6AQuiXnm"]}