Ian Goodfellow撰文总结：谷歌的 ICLR 2017 硕果累累

雷锋网消息，谷歌大脑团队的 Ian Goodfellow 今日在研究院官网上撰文，总结了谷歌在 ICLR 2017 上所做的学术贡献。雷锋网编译全文如下，未经许可不得转载。

本周，第五届国际学习表征会议（ICLR 2017）在法国土伦召开，这是一个关注机器学习领域如何从数据中习得具有意义及有用表征的会议。ICLR 包括 conference track 及 workshop track 两个项目，邀请了获得 oral 及 poster 的研究者们进行分享，涵盖深度学习、度量学习、核学习、组合模型、非线性结构化预测，及非凸优化问题。

站在神经网络及深度学习领域浪潮之巅，谷歌关注理论与实践，并致力于开发理解与总结的学习方法。作为 ICLR 2017 的白金赞助商，谷歌有超过 50 名研究者出席本次会议（大部分为谷歌大脑团队及谷歌欧洲研究分部的成员），通过在现场展示论文及海报的方式，为建设一个更完善的学术研究交流平台做出了贡献，也是一个互相学习的过程。此外，谷歌的研究者也是 workshops 及组委会构建的中坚力量。

如果你来到 ICLR 2017，我们希望你能在我们的展台前驻足，并与我们的研究者进行交流，探讨如何为数十亿人解决有趣的问题。

以下为谷歌在 ICLR 2017 展示的论文内容（其中的谷歌研究者已经加粗表示）

区域主席

George Dahl, Slav Petrov, Vikas Sindhwani

程序主席（雷锋网此前已经做过相关介绍）

Hugo Larochelle, Tara Sainath

受邀演讲论文

• Understanding Deep Learning Requires Rethinking Generalization (Best Paper Award)

  Chiyuan Zhang*, Samy Bengio, Moritz Hardt, Benjamin Recht*, Oriol Vinyals

• Semi-Supervised Knowledge Transfer for Deep Learning from Private Training Data (Best Paper Award)

  Nicolas Papernot*, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar

• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic

  Shixiang (Shane) Gu*, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine

• Neural Architecture Search with Reinforcement Learning

  Barret Zoph, Quoc Le

Poster 论文

• Adversarial Machine Learning at Scale

  Alexey Kurakin, Ian J. Goodfellow†, Samy Bengio

• Capacity and Trainability in Recurrent Neural Networks

  Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo

• Improving Policy Gradient by Exploring Under-Appreciated Rewards

  Ofir Nachum, Mohammad Norouzi, Dale Schuurmans

• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

  Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean

• Unrolled Generative Adversarial Networks

  Luke Metz, Ben Poole*, David Pfau, Jascha Sohl-Dickstein

• Categorical Reparameterization with Gumbel-Softmax

  Eric Jang, Shixiang (Shane) Gu*, Ben Poole*

• Decomposing Motion and Content for Natural Video Sequence Prediction

  Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee

• Density Estimation Using Real NVP

  Laurent Dinh*, Jascha Sohl-Dickstein, Samy Bengio

• Latent Sequence Decompositions

  William Chan*, Yu Zhang*, Quoc Le, Navdeep Jaitly*

• Learning a Natural Language Interface with Neural Programmer

  Arvind Neelakantan*, Quoc V. Le, Martín Abadi, Andrew McCallum*, Dario Amodei*

• Deep Information Propagation

  Samuel Schoenholz, Justin Gilmer, Surya Ganguli, Jascha Sohl-Dickstein

• Identity Matters in Deep Learning

  Moritz Hardt, Tengyu Ma

• A Learned Representation For Artistic Style

  Vincent Dumoulin*, Jonathon Shlens, Manjunath Kudlur

• Adversarial Training Methods for Semi-Supervised Text Classification

  Takeru Miyato, Andrew M. Dai, Ian Goodfellow†

• HyperNetworks

  David Ha, Andrew Dai, Quoc V. Le

• Learning to Remember Rare Events

  Lukasz Kaiser, Ofir Nachum, Aurko Roy*, Samy Bengio

Workshop Track

• Particle Value Functions

  Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh

• Neural Combinatorial Optimization with Reinforcement Learning

  Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio

• Short and Deep: Sketching and Neural Networks

  Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar

• Explaining the Learning Dynamics of Direct Feedback Alignment

  Justin Gilmer, Colin Raffel, Samuel S. Schoenholz, Maithra Raghu, Jascha Sohl-Dickstein

• Training a Subsampling Mechanism in Expectation

  Colin Raffel, Dieterich Lawson

• Tuning Recurrent Neural Networks with Reinforcement Learning

  Natasha Jaques*, Shixiang (Shane) Gu*, Richard E. Turner, Douglas Eck

• REBAR: Low-Variance, Unbiased Gradient Estimates for Discrete Latent Variable Models

  George Tucker, Andriy Mnih, Chris J. Maddison, Jascha Sohl-Dickstein

• Adversarial Examples in the Physical World

  Alexey Kurakin, Ian Goodfellow†, Samy Bengio

• Regularizing Neural Networks by Penalizing Confident Output Distributions

  Gabriel Pereyra, George Tucker, Jan Chorowski, Lukasz Kaiser, Geoffrey Hinton

• Unsupervised Perceptual Rewards for Imitation Learning

  Pierre Sermanet, Kelvin Xu, Sergey Levine

• Changing Model Behavior at Test-time Using Reinforcement Learning

  Augustus Odena, Dieterich Lawson, Christopher Olah

* 工作内容在谷歌就职时完成

† 工作内容在 OpenAI 任职时完成

详细信息可访问 research.googleblog 了解，雷锋网编译。