{"type":"ScholarlyArticle","title":"Reparameterizable Subset Sampling via Continuous Relaxations","authors":[{"name":"Sang Michael Xie","slug":"sang-michael-xie","given":"Sang Michael","family":"Xie","affiliation":"Stanford University"},{"name":"Stefano Ermon","slug":"stefano-ermon","given":"Stefano","family":"Ermon","affiliation":"Stanford University"}],"abstract":"Many machine learning tasks require sampling a subset of items from a collection based on a parameterized distribution. The Gumbel-softmax trick can be used to sample a single item, and allows for low-variance reparameterized gradients with respect to the parameters of the underlying distribution. However, stochastic optimization involving subset sampling is typically not reparameterizable. To overcome this limitation, we define a continuous relaxation of subset sampling that provides reparameterization gradients by generalizing the Gumbel-max trick. We use this approach to sample subsets of features in an instance-wise feature selection task for model interpretability, subsets of neighbors to implement a deep stochastic k-nearest neighbors model, and sub-sequences of neighbors to implement parametric t-SNE by directly comparing the identities of local neighbors. We improve performance in all these tasks by incorporating subset sampling in end-to-end training.","doi":"10.24963/ijcai.2019/544","url":"https://ijcai.org/proceedings/2019/544","pdf":"https://ijcai.org/proceedings/2019/0544.pdf","markdown":"https://ijcai.org/proceedings/2019/544.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/544","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning M-Z","track":"Main track","number":544,"pages":{"first":3919,"last":3925},"keywords":["Machine Learning: Deep Learning","Machine Learning: Structured Prediction","Machine Learning: Probabilistic Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Chen et al., 2018] Jianbo Chen, Le Song, Martin Wain- wright, and Michael Jordan. Learning to explain: An information-theoretic perspective on model interpretation. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learn- ing, volume 80 of Proceedings of Machine Learning Re- search, pages 883-892, Stockholmsmässan, Stockholm Sweden, 10-15 Jul 2018. PMLR.","title":"Learning to explain: An information-theoretic perspective on model interpretation","authors":"Jianbo Chen, Le Song, Martin Wainwright, Michael Jordan","year":"2018","venue":"Proceedings of the 35th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Efraimidis and Spirakis, 2006] Pavlos S. Efraimidis and Paul G. Spirakis. Weighted random sampling with a reser- voir. Information Processing Letters, 97(5):181 -185, 2006.","title":"Weighted random sampling with a reservoir","authors":"Pavlos S Efraimidis, Paul G Spirakis","year":"2006","venue":"Information Processing Letters","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Grover et al., 2019] Aditya Grover, Eric Wang, Aaron Zweig, and Stefano Ermon. Stochastic optimization of sorting networks via continuous relaxations. In Interna- tional Conference on Learning Representations, 2019.","title":"Stochastic optimization of sorting networks via continuous relaxations","authors":"Aditya Grover, Eric Wang, Aaron Zweig, Stefano Ermon","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Jang et al., 2016] Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparameterization with gumbel-softmax. CoRR, abs/1611.01144, 2016.","title":"Categorical reparameterization with gumbel-softmax","authors":"Eric Jang, Shixiang Gu, Ben Poole","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Kim et al., 2016] Carolyn Kim, Ashish Sabharwal, and Ste- fano Ermon. Exact sampling with integer linear programs and random perturbations. In Proceedings of the Thirti- eth AAAI Conference on Artificial Intelligence, AAAI'16, pages 3248-3254. AAAI Press, 2016.","title":"Exact sampling with integer linear programs and random perturbations","authors":"Carolyn Kim, Ashish Sabharwal, Stefano Ermon","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI'16","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kim, 2014] Yoon Kim. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Confer- ence on Empirical Methods in Natural Language Process- ing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1746-1751, 2014.","title":"Convolutional neural networks for sentence classification","authors":"Yoon Kim","year":"2014","venue":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kingma and Welling, 2013] Diederik P Kingma and Max Welling. Auto-encoding variational bayes, 2013. cite arxiv:1312.6114.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kingma et al., 2014] Durk P Kingma, Shakir Mohamed, Danilo Jimenez Rezende, and Max Welling. Semi- supervised learning with deep generative models. In Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, editors, Advances in Neural Infor- mation Processing Systems 27, pages 3581-3589.","title":"Semisupervised learning with deep generative models","authors":"Shakir Durk P Kingma, Danilo Mohamed, Max Jimenez Rezende, Welling","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Curran Associates, Inc., 2014.","title":null,"authors":"Curran Associates, Inc","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kool et al., 2019] Wouter Kool, Herke Van Hoof, and Max Welling. Stochastic beams and where to find them: The Gumbel-top-k trick for sampling sequences without re- placement. In Kamalika Chaudhuri and Ruslan Salakhut- dinov, editors, Proceedings of the 36th International Con- ference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 3499-3508, Long Beach, California, USA, 09-15 Jun 2019. PMLR.","title":"Stochastic beams and where to find them: The Gumbel-top-k trick for sampling sequences without replacement","authors":"Kool","year":"2019","venue":"Proceedings of the 36th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kusner and Hernández-Lobato, 2016] Matt J. Kusner and José Miguel Hernández-Lobato. GANS for sequences of discrete elements with the gumbel-softmax distribution. CoRR, abs/1611.04051, 2016.","title":"GANS for sequences of discrete elements with the gumbel-softmax distribution","authors":"Matt J Kusner, José Miguel Hernández-Lobato","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[LeCun and Cortes, 2010] Yann LeCun and Corinna Cortes. MNIST handwritten digit database. 2010.","title":"MNIST handwritten digit database","authors":"Lecun, Cortes, Yann Lecun, Corinna Cortes","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2015] Jiwei Li, Minh-Thang Luong, and Dan Ju- rafsky. A hierarchical neural autoencoder for paragraphs and documents. In ACL (1), pages 1106-1115. The Asso- ciation for Computer Linguistics, 2015.","title":"A hierarchical neural autoencoder for paragraphs and documents","authors":"Li","year":"2015","venue":"ACL (1)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Maas et al., 2011] Andrew L. Maas, Raymond E. Daly, Pe- ter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. Learning word vectors for sentiment analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Tech- nologies, pages 142-150, Portland, Oregon, USA, June 2011. Association for Computational Linguistics.","title":"Learning word vectors for sentiment analysis","authors":"Andrew L Maas, Raymond E Daly, Peter T Pham, Dan Huang, Andrew Y Ng, Christopher Potts","year":"2011","venue":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Maddison et al., 2017] Chris J. Maddison, Andriy Mnih, and Yee Whye Teh. The Concrete Distribution: A Contin- uous Relaxation of Discrete Random Variables. In Inter- national Conference on Learning Representations, 2017.","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","authors":"Chris J Maddison, Andriy Mnih, Yee Whye Teh","year":"2017","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Plötz and Roth, 2018] Tobias Plötz and Stefan Roth. Neu- ral nearest neighbors networks. In S. Bengio, H. Wal- lach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Pro- cessing Systems 31, pages 1095-1106.","title":"Neural nearest neighbors networks","authors":"Roth ; Plötz, Tobias Plötz, Stefan Roth","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Curran Associates, Inc., 2018.","title":null,"authors":"Curran Associates, Inc","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Roweis, 2009] Sam Roweis. Data for matlab hackers, 2009.","title":"Data for matlab hackers","authors":"Sam Roweis, Roweis","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[van der Maaten, 2009] Laurens van der Maaten. Learning a parametric embedding by preserving local structure. In David van Dyk and Max Welling, editors, Proceedings of the Twelth International Conference on Artificial In- telligence and Statistics, volume 5 of Proceedings of Ma- chine Learning Research, pages 384-391, Hilton Clearwa- ter Beach Resort, Clearwater Beach, Florida USA, 16-18 Apr 2009. PMLR.","title":"Learning a parametric embedding by preserving local structure","authors":"Van Der Maaten ; Laurens Van Der Maaten","year":"2009","venue":"Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Venna and Kaski, 2006] Jarkko Venna and Samuel Kaski. Visualizing gene interaction graphs with local multidimen- sional scaling. 2006.","title":"Visualizing gene interaction graphs with local multidimensional scaling","authors":"Kaski Venna, Jarkko Venna, Samuel Kaski","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Vieira, 2014] Tim Vieira. Gumbel-max trick and weighted reservoir sampling, 2014.","title":"Gumbel-max trick and weighted reservoir sampling","authors":"Tim Vieira","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vitter, 1985] Jeffrey S. Vitter. Random sampling with a reservoir. ACM Trans. Math. Softw., 11(1):37-57, March 1985.","title":"Random sampling with a reservoir","authors":"Jeffrey S Vitter","year":"1985","venue":"ACM Trans. Math. Softw","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Williams, 1992] Ronald J. Williams. Simple statistical gradient-following algorithms for connectionist reinforce- ment learning. Mach. Learn., 8(3-4):229-256, May 1992.","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","authors":"Ronald J Williams","year":"1992","venue":"Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu et al., 2015] Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S. Zemel, and Yoshua Bengio. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the 32Nd International Conference on International Conference on Machine Learning -Volume 37, ICML'15, pages 2048-2057. JMLR.org, 2015.","title":"Show, attend and tell: Neural image caption generation with visual attention","authors":"Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S Zemel, Yoshua Bengio","year":"2015","venue":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yellott, 1977] John I. Yellott. The relationship between luce's choice axiom, thurstone's theory of comparative judgment, and the double exponential distribution. Journal of Mathematical Psychology, 15(2):109 -144, 1977.","title":"The relationship between luce's choice axiom, thurstone's theory of comparative judgment, and the double exponential distribution","authors":"John I Yellott","year":"1977","venue":"Journal of Mathematical Psychology","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}