---
title: "ICML 2016 — all accepted papers with summaries and citations"
description: "All 83 papers of ICML 2016, the most cited first; those with our summary link to it. Among them: CryptoNets: applying neural networks to…"
canonical: "https://research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2016/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2016/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [ICML](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/) / [2016](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2016/) / papers

# ICML 2016: all accepted papers

83 papers · the most cited first · [← ICML 2016](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2016/)

1. **[CryptoNets: applying neural networks to encrypted data with high throughput and accuracy ↗](http://proceedings.mlr.press/v48/gilad-bachrach16.pdf)**Nathan Dowlin, Ran Gilad-Bachrach, Kim Laine et al.*1,228 citations*
2. **[Meta-learning with memory-augmented neural networks ↗](http://proceedings.mlr.press/v48/santoro16.pdf)**Adam Santoro, Sergey Bartunov, Matthew Botvinick et al.*1,121 citations*
3. **[Train faster, generalize better: stability of stochastic gradient descent ↗](http://jmlr.org/proceedings/papers/v48/hardt16.pdf)**Moritz Hardt, Benjamin Recht, Yoram Singer*364 citations*
4. **[33rd International Conference on Machine Learning, ICML 2016 ↗](https://research.aalto.fi/fi/publications/scalable-gradientbased-tuning-of-continuous-regularization-hyperparameters(42380b78-c7fe-476f-9321-24784d0e54ab).html)**Jelena Luketina, Mathias Berglund, Klaus Greff et al.*161 citations*
5. **[A kernelized stein discrepancy for goodness-of-fit tests ↗](http://proceedings.mlr.press/v48/liub16.pdf)**Qiang Liu, Jason D. Lee, Michael I. Jordan*142 citations*
6. **[Towards Automatically-Tuned Neural Networks ↗](http://proceedings.mlr.press/v64/mendoza_towards_2016.pdf)**Hector Mendoza, Aaron Klein, Matthias Feurer et al.*129 citations*
7. **[PD-sparse: a primal and dual sparse approach to extreme multiclass and multilabel classification ↗](http://proceedings.mlr.press/v48/yenb16.pdf)**Ian En-Hsu Yen, Xiangru Huang, Kai Zhong et al.*121 citations*
8. **[PHOG: probabilistic model for code ↗](http://proceedings.mlr.press/v48/bielik16.pdf)**Pavol Bielik, Veselin Raychev, Martin Vechev*101 citations*
9. **[Persistent RNNs: stashing recurrent weights on-chip ↗](http://proceedings.mlr.press/v48/diamos16.pdf)**Gregory Diamos, Shubho Sengupta, Bryan Catanzaro et al.*65 citations*
10. **[Learning end-to-end video classification with rank-pooling ↗](http://jmlr.org/proceedings/papers/v48/fernando16.pdf)**Basura Fernando, Stephen Gould*58 citations*
11. **[Isotonic hawkes processes ↗](http://proceedings.mlr.press/v48/wangg16.pdf)**Yichen Wang, Bo Xie, Nan Du et al.*45 citations*
12. **[Adaptive sampling for SGD by exploiting side information ↗](http://proceedings.mlr.press/v48/gopal16.pdf)**Siddharth Gopal*39 citations*
13. **[Efficient multi-instance learning for activity recognition from time series data using an auto-regressive hidden Markov model ↗](http://proceedings.mlr.press/v48/guan16.pdf)**Xinze Guan, Raviv Raich, Weng‐Keen Wong*36 citations*
14. **[Estimating structured vector autoregressive models ↗](http://proceedings.mlr.press/v48/melnyk16.pdf)**Igor Melnyk, Arindam Banerjee*35 citations*
15. **[Low-rank matrix approximation with stability ↗](http://proceedings.mlr.press/v48/lib16.pdf)**Dongsheng Li, Chao Chen, Qin Lv et al.*35 citations*
16. **[Efficient private empirical risk minimization for high-dimensional learning ↗](http://proceedings.mlr.press/v48/kasiviswanathan16.pdf)**Shiva Prasad Kasiviswanathan, Hongxia Jin*34 citations*
17. **[Robust principal component analysis with side information ↗](http://proceedings.mlr.press/v48/chiang16.pdf)**Kai-Yang Chiang, Cho‐Jui Hsieh, Inderjit S. Dhillon*32 citations*
18. **[A distributed variational inference framework for unifying parallel sparse Gaussian process regression models ↗](http://proceedings.mlr.press/v48/hoang16.pdf)**Trong Nghia Hoang, Quang Minh Hoang, Bryan Kian Hsiang Low*31 citations*
19. **[Conditional bernoulli mixtures for multi-label classification ↗](http://proceedings.mlr.press/v48/lij16.pdf)**Cheng Li, Bingyu Wang, Virgil Pavlu et al.*31 citations*
20. **[Speeding up k-means by approximating Euclidean distances via block vectors ↗](http://jmlr.org/proceedings/papers/v48/bottesch16.pdf)**Thomas Bottesch, Thomas Bühler, Markus Kächele*30 citations*
21. **[A comparative analysis and study of multiview CNN models for joint object categorization and pose estimation ↗](http://proceedings.mlr.press/v48/elhoseiny16.pdf)**Mohamed Elhoseiny, Tarek El-Gaaly, Amr Bakry et al.*29 citations*
22. **[Learning Population-Level Diffusions with Generative RNNs ↗](http://proceedings.mlr.press/v48/hashimoto16.pdf)**Tatsunori Hashimoto, David Kenneth Gifford, Tommi Jaakkola*28 citations*
23. **[ForecastICU: a prognostic decision support system for timely prediction of intensive care unit admission ↗](http://proceedings.mlr.press/v48/yoon16.pdf)**Jinsung Yoon, Ahmed M. Alaa, Scott B. Hu et al.*27 citations*
24. **[Linking losses for density ratio and class-probability estimation ↗](http://proceedings.mlr.press/v48/menon16.pdf)**Aditya Krishna Menon, Cheng Soon Ong*27 citations*
25. **[The information-theoretic requirements of subspace clustering with missing data ↗](http://proceedings.mlr.press/v48/pimentel-alarcon16.pdf)**Daniel Pimentel-Alarcón, Robert D. Nowak*27 citations*
26. **[Anytime optimal algorithms in stochastic multi-armed bandits ↗](http://jmlr.org/proceedings/papers/v48/degenne16.pdf)**Rémy Degenne, Vianney Perchet*26 citations*
27. **[Fast methods for estimating the numerical rank of large matrices ↗](http://proceedings.mlr.press/v48/ubaru16.pdf)**Shashanka Ubaru, Yousef Saad*26 citations*
28. **[ADIOS: architectures deep in output space ↗](http://proceedings.mlr.press/v48/cisse16.pdf)**Moustapha Cissé, Maruan Al-Shedivat, Samy Bengio*25 citations*
29. **[Learning and inference via maximum inner product search ↗](http://proceedings.mlr.press/v48/mussmann16.pdf)**Stephen Mussmann, Stefano Ermon*25 citations*
30. **[No oops, you won't do it again: mechanisms for self-correction in crowdsourcing ↗](https://jmlr.org/proceedings/papers/v48/shaha16.pdf)**Nihar B. Shah, Dengyong Zhou*24 citations*
31. **[Estimating accuracy from unlabeled data: a Bayesian approach ↗](http://proceedings.mlr.press/v48/platanios16.pdf)**Emmanouil Antonios Platanios, Avinava Dubey, Tom M. Mitchell*23 citations*
32. **[A self-correcting variable-metric algorithm for stochastic optimization ↗](http://proceedings.mlr.press/v48/curtis16.pdf)**Frank E. Curtis*21 citations*
33. **[Quadratic optimization with orthogonality constraints: explicit Łojasiewicz exponent and linear convergence of line-search methods ↗](http://proceedings.mlr.press/v48/liue16.pdf)**Huikang Liu, Weijie Wu, Anthony Man–Cho So*21 citations*
34. **[Truthful univariate estimators ↗](http://proceedings.mlr.press/v48/caragiannis16.pdf)**Ioannis Caragiannis, Ariel D. Procaccia, Nisarg Shah*20 citations*
35. **[A Superlinearly-Convergent Proximal Newton-type Method for the Optimization of Finite Sums ↗](http://proceedings.mlr.press/v48/rodomanov16.pdf)**Anton Rodomanov, Dmitry Kropotov*19 citations*
36. **[Algorithms for optimizing the ratio of submodular functions ↗](http://proceedings.mlr.press/v48/baib16.pdf)**Wenruo Bai, Rishabh Iyer, Kai Wei et al.*19 citations*
37. **[Stochastic optimization for multiview representation learning using partial least squares ↗](http://proceedings.mlr.press/v48/aroraa16.pdf)**Raman Arora, Poorya Mianjy, Teodor V. Marinov*19 citations*
38. **[BASC: applying Bayesian optimization to the search for global minima on potential energy surfaces ↗](http://jmlr.org/proceedings/papers/v48/carr16.pdf)**Shane Carr, Roman Garnett, Cynthia S. Lo*18 citations*
39. **[The variational Nyström method for large-scale spectral problems ↗](http://proceedings.mlr.press/v48/vladymyrov16.pdf)**Max Vladymyrov, Miguel Á. Carreira-Perpiñán*17 citations*
40. **[Bounded Off-Policy Evaluation with Missing Data for Course Recommendation and Curriculum Design ↗](http://jmlr.org/proceedings/papers/v48/hoiles16.pdf)**William Hoiles, Mihaela van der Schaar*16 citations*
41. **[Analysis of Deep Neural Networks with Extended Data Jacobian Matrix ↗](https://jmlr.org/proceedings/papers/v48/wanga16.pdf)**Shengjie Wang, Abdelrahman Mohamed, Rich Caruana et al.*15 citations*
42. **[On the consistency of feature selection with lasso for non-linear targets ↗](http://jmlr.org/proceedings/papers/v48/zhanga16.pdf)**Yue Zhang, Soumya Ray, Weihong Guo*15 citations*
43. **[Correcting forecasts with multifactor neural attention ↗](http://jmlr.org/proceedings/papers/v48/riemer16.pdf)**Matthew Riemer, Aditya Vempaty, Flávio P. Calmon et al.*14 citations*
44. **[Diversity-promoting Bayesian learning of latent variable models ↗](http://proceedings.mlr.press/v48/xiea16.pdf)**Pengtao Xie, Jun Zhu, Eric P. Xing*14 citations*
45. **[On the analysis of complex backup strategies in Monte Carlo tree search ↗](http://proceedings.mlr.press/v48/khandelwal16.pdf)**Piyush Khandelwal, Elad Liebman, Scott Niekum et al.*13 citations*
46. **[Sequence to sequence training of CTC-RNNs with partial windowing ↗](http://proceedings.mlr.press/v48/hwanga16.pdf)**Kyuyeon Hwang, Wonyong Sung*13 citations*
47. **[The knowledge gradient for sequential decision making with stochastic binary feedbacks ↗](http://proceedings.mlr.press/v48/wangb16.pdf)**Yingfei Wang, Chu Wang, Warren B. Powell*13 citations*
48. **[A Strategy for Ranking Optimization Methods using Multiple Criteria ↗](http://proceedings.mlr.press/v64/dewancker_strategy_2016.pdf)**Ian Dewancker, Michael McCourt, Scott Clark et al.*12 citations*
49. **[Gaussian quadrature for matrix inverse forms with applications ↗](http://proceedings.mlr.press/v48/lig16.pdf)**Chengtao Li, Suvrit Sra, Stefanie Jegelka*11 citations*
50. **[No-regret algorithms for heavy-tailed linear bandits ↗](http://proceedings.mlr.press/v48/medina16.pdf)**Andrés Muñoz Medina, Scott Cheng‐Hsin Yang*11 citations*
51. **[K-means clustering with distributed dimensions ↗](http://proceedings.mlr.press/v48/ding16.pdf)**Hu Ding, Yu Liu, Lingxiao Huang et al.*9 citations*
52. **[Non-negative matrix factorization under heavy noise ↗](http://proceedings.mlr.press/v48/bhattacharya16.pdf)**Chiranjib Bhattacharyya, Navin Goyal, Ravindran Kannan et al.*9 citations*
53. **[Tensor decomposition via joint matrix schur decomposition ↗](http://proceedings.mlr.press/v48/colombo16.pdf)**Nicolò Colombo, Nikos A. Vlassis*9 citations*
54. **[Computationally efficient Nyström approximation using fast transforms ↗](http://jmlr.org/proceedings/papers/v48/si16.pdf)**Si Si, Cho‐Jui Hsieh, Inderjit S. Dhillon*8 citations*
55. **[Beyond parity constraints: Fourier analysis of hash functions for inference ↗](http://proceedings.mlr.press/v48/achim16.pdf)**Tudor Achim, Ashish Sabharwal, Stefano Ermon*7 citations*
56. **[The label complexity of mixed-initiative classifier training ↗](http://proceedings.mlr.press/v48/suh16.pdf)**Jina Suh, Xiaojin Zhu, Saleema Amershi*7 citations*
57. **[A box-constrained approach for hard permutation problems ↗](http://proceedings.mlr.press/v48/lim16.pdf)**Cong Han Lim, Stephen J. Wright*6 citations*
58. **[Controlling the distance to a Kemeny consensus without computing it ↗](http://proceedings.mlr.press/v48/korba16.pdf)**Yunlong Jiao, Anna Korba, Eric Sibony*6 citations*
59. **[Energetic natural gradient descent ↗](http://jmlr.org/proceedings/papers/v48/thomasb16.pdf)**Philip S. Thomas, Bruno Castro da Silva, Christoph Dann et al.*6 citations*
60. **[Pricing a low-regret seller ↗](http://proceedings.mlr.press/v48/heidari16.pdf)**Hoda Heidari, Mohammad Mahdian, Umar Syed et al.*6 citations*
61. **[Asymmetric Multi-task Learning based on Task Relatedness and Confidence. ↗](http://proceedings.mlr.press/v48/leeb16.pdf)**Giwoong Lee, Eunho Yang, Sung Ju Hwang*5 citations*
62. **[Stochastic discrete clenshaw-curtis quadrature ↗](http://proceedings.mlr.press/v48/piatkowski16.pdf)**Nico Piatkowski, Katharina J. Morik*5 citations*
63. **[Extended and unscented kitchen sinks ↗](http://proceedings.mlr.press/v48/bonilla16.pdf)**Edwin V. Bonilla, Daniel Steinberg, Alistair Reid*4 citations*
64. **[Learning population-level diffusions with generative recurrent networks ↗](https://jmlr.org/proceedings/papers/v48/hashimoto16.pdf)**Tatsunori Hashimoto, David Kenneth Gifford, Tommi Jaakkola*4 citations*
65. **[Matrix eigen-decomposition via doubly stochastic riemannian optimization ↗](http://proceedings.mlr.press/v48/xub16.pdf)**Zhiqiang Xu, Peilin Zhao, Jianneng Cao et al.*4 citations*
66. **[PAC lower bounds and efficient algorithms for the max K-armed bandit problem ↗](http://proceedings.mlr.press/v48/david16.pdf)**Yahel David, Nahum Shimkin*4 citations*
67. **[Sparse parameter recovery from aggregated data ↗](http://proceedings.mlr.press/v48/bhowmik16.pdf)**Avradeep Bhowmik, Joydeep Ghosh, Sanmi Koyejo*4 citations*
68. **[Accurate robust and efficient error estimation for decision trees ↗](http://proceedings.mlr.press/v48/fan16.pdf)**Lixin Fan*3 citations*
69. **[Barron and cover's theory in supervised learning and its application to lasso ↗](http://proceedings.mlr.press/v48/kawakita16.pdf)**Masanori Kawakita, Jun’ichi Takeuchi*3 citations*
70. **[Epigraph projections for fast general convex programming ↗](http://proceedings.mlr.press/v48/wangh16.pdf)**Po-Wei Wang, Matt Wytock, J. Zico Kolter*3 citations*
71. **[Optimal classification with multivariate losses ↗](http://proceedings.mlr.press/v48/natarajan16.pdf)**Nagarajan Natarajan, Sanmi Koyejo, Pradeep Ravikumar et al.*3 citations*
72. **[Scalable Structure Discovery in Regression using Gaussian Processes ↗](http://proceedings.mlr.press/v64/kim_scalable_2016.pdf)**Hyunjik Kim, Yee Whye Teh*3 citations*
73. **[Fast rate analysis of some stochastic optimization algorithms ↗](http://proceedings.mlr.press/v48/qua16.pdf)**Chao Qu, Huan Xu, Chong Jin Ong*2 citations*
74. **[Heteroscedastic sequences: beyond Gaussianity ↗](http://proceedings.mlr.press/v48/anava16.pdf)**Oren Anava, Shie Mannor*2 citations*
75. **[Markov latent feature models ↗](http://proceedings.mlr.press/v48/zhangf16.pdf)**Aonan Zhang, John William Paisley*2 citations*
76. **[Meta-gradient boosted decision tree model for weight and target learning ↗](http://jmlr.org/proceedings/papers/v48/ustinovskiy16.pdf)**Yury Ustinovskiy, Valentina Fedorova, Gleb Gusev et al.*2 citations*
77. **[Parameter-Free Convex Learning through Coin Betting ↗](http://proceedings.mlr.press/v64/orabona_parameter_2016.pdf)**Francesco Orabona, Dávid Pál*1 citation*
78. **[Analysis of VB factorizations for sparse and low-rank estimation ↗](http://jmlr.org/proceedings/papers/v48/wipf16.pdf)**David Wipf
79. **[Analysis of Variational Bayesian Factorizations for Sparse and Low-Rank Estimation ↗](http://proceedings.mlr.press/v48/wipf16.pdf)**David Wipf
80. **[Interactive Semantic Featuring for Text Classification ↗](https://www.microsoft.com/en-us/research/publication/interactive-semantic-featuring-text-classification/)**Patrice Simard, Max Chickering, Jina Suh
81. **[Mixing rates for the alternating Gibbs sampler over restricted Boltzmann machines and friends ↗](http://proceedings.mlr.press/v48/tosh16.pdf)**Christopher Tosh
82. **[On the statistical limits of convex relaxations: a case study ↗](https://www.scholars.northwestern.edu/en/publications/on-the-statistical-limits-of-convex-relaxations-a-case-study)**Zhaoran Wang, Quanquan Gu, Han Liu
83. **[Personalization of Search Results using Interactive Intent Modeling ↗](https://research.aalto.fi/files/9490802/ICML2016_preprint.pdf)**Antti Kangasrääsiö, Dorota Głowacka, Samuel Kaski
- [← back to](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2016/) — ICML 2016