19篇ICML2019论文摘录选读！

【导读】机器学习领域的国际顶级会议International Conference on Machine Learning (ICML)公布了2019年的论文评审结果，本年度ICML共收到3400篇左右的投稿，经过严格筛选，共有773篇论文被录用。专知整理一些公布的接受论文，欢迎查看！

1、Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin

作者：吴西竹，周志华，柳松

2、Importance Sampling Policy Evaluation with an Estimated Behavior Policy

arxiv.org/abs/1806.01347 

作者：Josiah Hanna, Scott Niekum, Peter Stone

3、Imitating Latent Policies from Observation

https://arxiv.org/abs/1805.07914

Ashley D. Edwards, Himanshu Sahni, Yannick Schroecker, Charles L. Isbell

4、Using Pre-Training Can Improve Model Robustness and Uncertainty

arxiv.org/abs/1901.09960 

作者：Dan Hendrycks, Kimin Lee, Mantas Mazeika

5、Hyperbolic Disk Embeddings for Directed Acyclic Graphs

arxiv.org/abs/1902.04335 

作者：Ryota Suzuki, Ryusuke Takahama, Shun Onoda

6、Finding Options that Minimize Planning Time

arxiv.org/abs/1810.07311 

作者：Yuu Jinnai, David Abel, D Ellis Hershkowitz, Michael Littman, George Konidaris

7、Discovering Options for Exploration by Minimizing Cover Time

https://arxiv.org/abs/1903.00606 

作者：Yuu Jinnai, Jee Won Park, David Abel, George Konidaris

8. Making Convolutional Networks Shift-Invariant Again

    作者：Richard Zhang

  地址：https://arxiv.org/abs/1904.11486

9、Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

arxiv.org/abs/1904.06387 

作者：Daniel S. Brown, Wonjoon Goo, Prabhat Nagarajan, Scott Niekum

10、Global Convergence of Block Coordinate Descent in Deep Learning

arxiv.org/abs/1803.00225 

作者：Jinshan Zeng, Tim Tsz-Kit Lau, Shaobo Lin, Yuan Yao

11、Learn-to-Grow for addressing Catastrophic Forgetting in Continual Machine Learning

https://arxiv.org/abs/1904.00310

作者：Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher, Caiming Xiong

12、Unsupervised label noise modeling and loss correction

https://arxiv.org/abs/1904.11238

作者：Eric Arazo, Diego Ortego, Paul Albert, Noel E. O'Connor, Kevin McGuinness

13、Bayesian leave-one-out cross-validation for large data  

https://arxiv.org/abs/1904.10679

作者：Måns Magnusson, Michael Riis Andersen, Johan Jonasson, Aki Vehtari

 14、Neural Collaborative Subspace Clustering

https://arxiv.org/abs/1904.10596

作者：Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, Hongdong Li

15、Imitation Learning from Imperfect Demonstration

https://arxiv.org/abs/1901.09387 

作者：Yueh-Hua Wu, Nontawat Charoenphakdee, Han Bao, Voot Tangkaratt, Masashi Sugiyama

16. Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks

arxiv.org/abs/1903.10047 

作者：Kenta Oono, Taiji Suzuki

17. Self-Attention Generative Adversarial Networks

arxiv.org/abs/1805.08318 

作者：Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena

18、TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

https://arxiv.org/abs/1807.10875 

作者：Augustus Odena, Ian Goodfellow

19、Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

https://arxiv.org/abs/1903.10346 

作者：Yao Qin, Nicholas Carlini, Ian Goodfellow, Garrison Cottrell, Colin Raffel

-END-

专 · 知

专知，专业可信的人工智能知识分发，让认知协作更快更好！欢迎登录www.zhuanzhi.ai，注册登录专知，获取更多AI知识资料！

欢迎微信扫一扫加入专知人工智能知识星球群，获取最新AI专业干货知识教程视频资料和与专家交流咨询！

请加专知小助手微信（扫一扫如下二维码添加），加入专知人工智能主题群，咨询技术商务合作~

专知《深度学习:算法到实战》课程全部完成！530+位同学在学习，现在报名，限时优惠！网易云课堂人工智能畅销榜首位！

点击“阅读原文”，了解报名专知《深度学习:算法到实战》课程