其他

NIPS 2017上演:Google大神们将带来哪些「精彩」?

2017-12-05 雷克世界



原文来源:Google Research Blog

作者:Christian Howard

「雷克世界」编译:嗯~阿童木呀、我是卡布达


本周,第31届神经信息处理系统年会(NIPS 2017)(https://nips.cc/Conferences/2017)将于加利福尼亚州长滩市举办,这是一个机器学习和计算神经科学会议,会议内容将涵盖邀约嘉宾演讲、成果演示以及一些最新的机器学习研究报告。Google在2017年NIPS大会将展现出色的影响力,约有450多名Google员工将会通过技术讲座、海报、研讨会、比赛以及教程等方式向更广泛的学术研究界人士学习与交流。

 

众所周知,Google处于机器学习的最前沿,积极地在从经典算法到深度学习等领域进行全面探索。注重理论和应用的协调发展,我们在语言理解、语音、翻译、视觉处理和预测方面的大部分研究都依赖于当前最先进的技术,以尽可能地扩展发展边界。在所有这些任务和其他许多任务中,我们开发了学习方法从而进行理解和归纳,从而为我们提供了新方法,以便查看旧问题和帮助改变我们现有的工作和生活方式。

 

如果你对大会感兴趣,可以从下面的列表信息进行详细了解。

 

注:Google是NIPS 2017的白金赞助商。

 

组织委员会

 

•执行主席:Samy Bengio


•高级领域主席包括:Corinna Cortes、Dale Schuurmans、Hugo Larochelle


•领域主席包括:Afshin Rostamizadeh、Amir Globerson、Been Kim、D. Sculley、Dumitru Erhan、Gal Chechik、Hartmut Neven、Honglak Lee、Ian Goodfellow、Jasper Snoek、John Wright、Jon Shlens、Kun Zhang、Lihong Li、Maya Gupta、Moritz Hardt、Navdeep Jaitly、Ryan Adams、Sally Goldman、Sanjiv Kumar、Surya Ganguli、Tara Sainath、Umar Syed、Viren Jain、Vitaly Kuznetsov

 

邀约嘉宾演讲

 

《助力未来100年》——John Platt

https://nips.cc/Conferences/2017/Schedule?showEvent=8729

 

接受的论文

 

•《元学习视角下的项目冷启动推荐》A Meta-Learning Perspective on Cold-Start Recommendations for Items

http://papers.nips.cc/paper/7266-a-meta-learning-perspective-on-cold-start-recommendations-for-items

Manasi Vartak、Hugo Larochelle、ArvindThiagarajan

 

•《AdaGAN:Boosting Generative Models》

http://papers.nips.cc/paper/7126-adagan-boosting-generative-models

Ilya Tolstikhin、SylvainGelly、Olivier Bousquet、Carl-Johann Simon-Gabriel、BernhardSchölkopf

 

•《深度Lattice网络和局部单调函数》Deep Lattice Networks and PartialMonotonic Functions

http://papers.nips.cc/paper/6891-deep-lattice-networks-and-partial-monotonic-functions

Seungil You、David Ding、Kevin Canini、Jan Pfeifer、Maya Gupta

 

•《你的图表出自何处》From which world is your graph

http://papers.nips.cc/paper/6745-from-which-world-is-your-graph

Cheng Li、Varun Kanade、Felix MFWong、Zhenming Liu

 

•《于众目睽睽之下隐藏图像:深度隐写术》Hiding Images in Plain Sight: Deep Steganography

http://papers.nips.cc/paper/6802-hiding-images-in-plain-sight-deep-steganography

Shumeet Baluja

 

•《通过几何自一致性得以改进的图的拉普拉斯矩阵》Improved Graph Laplacian via Geometric Self-Consistency

http://papers.nips.cc/paper/7032-improved-graph-laplacian-via-geometric-self-consistency

Dominique Joncas、MarinaMeila、James McQueen

 

•《模型驱动下的条件性独立性测试》Model-Powered Conditional Independence Test

http://papers.nips.cc/paper/6888-model-powered-conditional-independence-test

Rajat Sen、Ananda TheerthaSuresh、Karthikeyan Shanmugam、Alexandros Dimakis、Sanjay Shakkottai

 

•《深度学习非线性随机矩阵理论》Nonlinear random matrix theory for deep learning

http://papers.nips.cc/paper/6857-nonlinear-random-matrix-theory-for-deep-learning

Jeffrey Pennington、Pratik Worah

 

•《通过动态等距“复活”深度学习中的sigmoid函数:理论与实践》Resurrecting the sigmoid in deep learning through dynamicalisometry: theory and practice

http://papers.nips.cc/paper/7064-resurrecting-the-sigmoid-in-deep-learning-through-dynamical-isometry-theory-and-practice

Jeffrey Pennington、SamuelSchoenholz、Surya Ganguli

 

•《用SGD学习网络的共轭内核类》SGD Learns the Conjugate Kernel Class of the Network

http://papers.nips.cc/paper/6836-sgd-learns-the-conjugate-kernel-class-of-the-network

Amit Daniely

 

•《SVCCA:深度学习动力学和可解释性的奇异向量典型相关分析》SVCCA: Singular Vector Canonical Correlation Analysis for DeepLearning Dynamics and Interpretability

http://papers.nips.cc/paper/7188-svcca-singular-vector-canonical-correlation-analysis-for-deep-learning-dynamics-and-interpretability

Maithra Raghu、Justin Gilmer、JasonYosinski、Jascha Sohl-Dickstein

 

•《用循环神经模块学习分层信息流》Learning Hierarchical Information Flow with Recurrent Neural Modules

http://papers.nips.cc/paper/7249-learning-hierarchical-information-flow-with-recurrent-neural-modules

Danijar Hafner、AlexanderIrpan、James Davidson、Nicolas Heess

 

•《Online Learning with Transductive Regret》

http://papers.nips.cc/paper/7106-online-learning-with-transductive-regret

Scott Yang、Mehryar Mohri

 

•《随机下降动力学中的加速和平均》Acceleration and Averaging in Stochastic Descent Dynamics

http://papers.nips.cc/paper/7256-acceleration-and-averaging-in-stochastic-descent-dynamics

Walid Krichene、Peter Bartlett

 

•《通过模型选择进行无参数在线学习》Parameter-Free Online Learning via Model Selection

http://papers.nips.cc/paper/7183-parameter-free-online-learning-via-model-selection

Dylan J Foster、Satyen Kale、MehryarMohri、Karthik Sridharan

 

•《胶囊之间的动态路由》Dynamic Routing Between Capsules

http://papers.nips.cc/paper/6975-dynamic-routing-between-capsules

Sara Sabour、Nicholas Frosst、Geoffrey EHinton

 

•《通过语言调整早期视觉处理》Modulating early visual processing by language

http://papers.nips.cc/paper/7237-modulating-early-visual-processing-by-language

Harm de Vries、Florian Strub、Jeremie Mary、HugoLarochelle、Olivier Pietquin、Aaron C Courville

 

•《MarrNet:通过2.5DSketches进行3D形状重建》MarrNet: 3D Shape Reconstruction via 2.5D Sketches

http://papers.nips.cc/paper/6657-marrnet-3d-shape-reconstruction-via-25d-sketches

Jiajun Wu、Yifan Wang、Tianfan Xue、Xingyuan Sun、Bill Freeman、JoshTenenbaum

 

•《亲和聚类:规模性分层聚类》Affinity Clustering: Hierarchical Clustering at Scale

http://papers.nips.cc/paper/7262-affinity-clustering-hierarchical-clustering-at-scale

Mahsa Derakhshan、SoheilBehnezhad、Mohammadhossein Bateni、Vahab Mirrokni、MohammadTaghi Hajiaghayi、Silvio Lattanzi、RaimondasKiveris

 

•《用于映射推理的异步并行坐标最小化》Asynchronous Parallel Coordinate Minimization for MAP Inference

http://papers.nips.cc/paper/7156-asynchronous-parallel-coordinate-minimization-for-map-inference

Ofer Meshi、Alexander Schwing

 

•《用Softmax策略梯度进行冷启动强化学习》Cold-Start Reinforcement Learning with Softmax Policy Gradient

http://papers.nips.cc/paper/6874-cold-start-reinforcement-learning-with-softmax-policy-gradient

Nan Ding、Radu Soricut

 

•《过滤变分目标》Filtering Variational Objectives

http://papers.nips.cc/paper/7235-filtering-variational-objectives

Chris J Maddison、DieterichLawson、George Tucker、Mohammad Norouzi、Nicolas Heess、Andriy Mnih、Yee Whishe、Arnaud Doucet

 

•《Multi-Armed Bandits with Metric Movement Costs》

http://papers.nips.cc/paper/7000-multi-armed-bandits-with-metric-movement-costs

Tomer Koren、Roi Livni、YishayMansour

 

•《用于快速相似搜索的多尺度量化》Multiscale Quantization for Fast Similarity Search

http://papers.nips.cc/paper/7157-multiscale-quantization-for-fast-similarity-search

Xiang Wu、Ruiqi Guo、AnandaTheertha Suresh、Sanjiv Kumar、Daniel Holtmann-Rice、David Simcha、Felix Yu

 

•《减少重新参数化的梯度方差》Reducing Reparameterization Gradient Variance

http://papers.nips.cc/paper/6961-reducing-reparameterization-gradient-variance

Andrew Miller、Nicholas Foti、AlexanderD'Amour、Ryan Adams

 

•《分担统计成本》Statistical Cost Sharing

http://papers.nips.cc/paper/7202-statistical-cost-sharing

Eric Balkanski、Umar Syed、SergeiVassilvitskii

 

•《结构随机正交嵌入的不合理有效性》The Unreasonable Effectiveness of Structured Random OrthogonalEmbeddings

http://papers.nips.cc/paper/6626-the-unreasonable-effectiveness-of-structured-random-orthogonal-embeddings

Krzysztof Choromanski、MarkRowlandAdrian Weller

 

•《值预测网络》Value Prediction Network

http://papers.nips.cc/paper/7192-value-prediction-network

Junhyuk Oh、Satinder Singh、Honglak Lee

 

•《REBAR:离散潜变量模型的低方差、无偏差梯度估计》REBAR: Low-variance, unbiased gradient estimates for discrete latentvariable models

http://papers.nips.cc/paper/6856-rebar-low-variance-unbiased-gradient-estimates-for-discrete-latent-variable-models

George Tucker、Andriy Mnih、Chris JMaddison、Dieterich Lawson、Jascha Sohl-Dickstein

 

•《生成式对抗性学习的近似与收敛》Approximation and Convergence Properties of Generative AdversarialLearning

http://papers.nips.cc/paper/7138-approximation-and-convergence-properties-of-generative-adversarial-learning

Shuang Liu、Olivier Bousquet、KamalikaChaudhuri

 

•《无可或缺的注意力》Attention is All you Need

http://papers.nips.cc/paper/7181-attention-is-all-you-need

Ashish Vaswani、Noam Shazeer、Niki Parmar、JakobUszkoreit、Llion Jones、Aidan N Gomez、ŁukaszKaiser、Illia Polosukhin

 

•《PASS-GLM:用于扩展性贝叶斯GLM推理的多项式近似充分统计》PASS-GLM: polynomial approximate sufficient statistics for scalableBayesian GLM inference

http://papers.nips.cc/paper/6952-pass-glm-polynomial-approximate-sufficient-statistics-for-scalable-bayesian-glm-inference

Jonathan Huggins、Ryan Adams、TamaraBroderick

 

•《重复逆向强化学习》Repeated Inverse Reinforcement Learning

http://papers.nips.cc/paper/6778-repeated-inverse-reinforcement-learning

Kareem Amin、Nan Jiang、SatinderSingh

 

•《通过Fairlets进行公平聚类》Fair Clustering Through Fairlets

http://papers.nips.cc/paper/7088-fair-clustering-through-fairlets

Flavio Chierichetti、Ravi Kumar、SilvioLattanzi、Sergei Vassilvitskii

 

•《仿射不变在线优化和低秩专家问题》Affine-Invariant Online Optimization and the Low-rank ExpertsProblem

http://papers.nips.cc/paper/7060-affine-invariant-online-optimization-and-the-low-rank-experts-problem

Tomer Koren、Roi Livni

 

•《批量重新正则化:在批量正则化模型中降低小批量依赖性》Batch Renormalization: Towards Reducing Minibatch Dependence inBatch-Normalized Models

http://papers.nips.cc/paper/6790-batch-renormalization-towards-reducing-minibatch-dependence-in-batch-normalized-models

Sergey Ioffe

 

•《值与基于策略的强化学习间鸿沟的弥合》Bridging the Gap Between Value and Policy Based ReinforcementLearning

http://papers.nips.cc/paper/6870-bridging-the-gap-between-value-and-policy-based-reinforcement-learning

Ofir Nachum、Mohammad Norouzi、Kelvin Xu、DaleSchuurmans

 

•《鉴别式状态空间模型》Discriminative State Space Models

http://papers.nips.cc/paper/6870-bridging-the-gap-between-value-and-policy-based-reinforcement-learning

Vitaly Kuznetsov、MehryarMohri

 

•《动态收益分享》Dynamic Revenue Sharing

http://papers.nips.cc/paper/6861-dynamic-revenue-sharing

Santiago Balseiro、Max Lin,Vahab Mirrokni、Renato Leme、Song Zuo

 

•《用于线性动力系统估计的多视图矩阵分解》Multi-view Matrix Factorization for Linear Dynamical SystemEstimation

http://papers.nips.cc/paper/7284-multi-view-matrix-factorization-for-linear-dynamical-system-estimation

Mahdi Karami、Martha White、DaleSchuurmans、Csaba Szepesvari

 

•《黑箱反向传播和雅可比传感》On Blackbox Backpropagation and Jacobian Sensing

http://papers.nips.cc/paper/7230-on-blackbox-backpropagation-and-jacobian-sensing

Krzysztof Choromanski、VikasSindhwani

 

•《快速移位的一致性》On the Consistency of Quick Shift

http://papers.nips.cc/paper/6610-on-the-consistency-of-quick-shift

Heinrich Jiang

 

•《用近似出价预测的收益优化》Revenue Optimization with Approximate Bid Predictions

http://papers.nips.cc/paper/6782-revenue-optimization-with-approximate-bid-predictions

Andres Munoz、Sergei Vassilvitskii

 

•《声音的形状和材质》Shape and Material from Sound

http://papers.nips.cc/paper/6727-shape-and-material-from-sound

Zhoutong Zhang、Qiujia Li、ZhengjiaHuang、Jiajun Wu、Josh Tenenbaum、Bill Freeman

 

•《学习通过视觉去动画来看物理》Learning to See Physics via Visual De-animation

http://papers.nips.cc/paper/6620-learning-to-see-physics-via-visual-de-animation

Jiajun Wu、Erika Lu、PushmeetKohli、Bill Freeman、Josh Tenenbaum

 

会议演示

 

•具有高效和鲁棒性的移动视觉的电子屏幕保护器

https://nips.cc/Conferences/2017/Schedule?showEvent=9757

Hee Jung Ryu、Florian Schroff

 

•Magenta和deeplearn.js:实时控制浏览器中的深度音乐模型

https://nips.cc/Conferences/2017/Schedule?showEvent=9762

Curtis Hawthorne、Ian Simon、Adam Roberts、Jesse Engel、DanielSmilkov、Nikhil Thorat、Douglas Eck

 

研讨会

 

•2017年第六届自动知识库建设(AKBC)研讨会

https://nips.cc/Conferences/2017/Schedule?showEvent=8785

项目委员会包括:Arvind Neelakanta

作者包括:Jiazhong Nie、Ni Lao

 

•现实世界中的行为与交互:机器人学习所面临的挑战

https://nips.cc/Conferences/2017/Schedule?showEvent=8764

特邀演讲嘉宾包括:Pierre Sermanet

 

•近似贝叶斯推理的进展

https://nips.cc/Conferences/2017/Schedule?showEvent=8781

小组主持人:Matthew D. Hoffman

 

•会话AI——当前的实践和未来的潜力

https://nips.cc/Conferences/2017/Schedule?showEvent=8757

特邀演讲嘉宾包括:Matthew Henderson、Dilek Hakkani-Tur

主办单位包括:Larry Heck

 

•极端分类:极大标记空间中进行多类和多标记学习

https://nips.cc/Conferences/2017/Schedule?showEvent=8759

特邀演讲嘉宾包括:Ed Chi、Mehryar Mohri

 

•战略行为层面的学习Learning in the Presence of Strategic Behavior

https://nips.cc/Conferences/2017/Schedule?showEvent=8784

特邀演讲嘉宾包括:Mehryar Mohri

主持人包括:Andres Munoz Medina、Sebastien Lahaie、Sergei Vassilvitskii、Balasubramanian Sivan

 

•在分布式、函数、图形和群组方面的学习Learning on Distributions, Functions, Graphs and Groups

https://nips.cc/Conferences/2017/Schedule?showEvent=8770

特邀演讲嘉宾包括:Corinna Cortes

 

•机器欺骗Machine Deception

https://nips.cc/Conferences/2017/Schedule?showEvent=8763

主办单位包括:Ian Goodfellow

特邀演讲嘉宾包括:Jacob Buckman、Aurko Roy、Colin Raffel、Ian Goodfellow

 

•机器学习和计算机安全Machine Learning and Computer Security

https://nips.cc/Conferences/2017/Schedule?showEvent=8775

特邀演讲嘉宾包括:Ian Goodfellow

主办单位包括:Nicolas Papernot

作者包括:Jacob Buckman、Aurko Roy、Colin Raffel、Ian Goodfellow

 

•创意性和设计性机器学习Machine Learning for Creativity and Design

https://nips.cc/Conferences/2017/Schedule?showEvent=8777

主讲人包括:Ian Goodfellow

主办方包括:Doug Eck、David Ha

 

•用于音频信号处理的机器学习(ML4Audio)Machine Learning for Audio Signal Processing

https://nips.cc/Conferences/2017/Schedule?showEvent=8790

作者包括:Aren Jansen、Manoj Plakal、Dan Ellis、Shawn Hershey、Channing Moore、Rif A. Saurous、Yuxuan Wang、RJ Skerry-Ryan、Ying Xiao、Daisy Stanton、Joel Shor、Eric Batternberg、Rob Clark

 

•健康领域的机器学习(ML4H)Machine Learning for Health

https://nips.cc/Conferences/2017/Schedule?showEvent=9561

组织者包括:Jasper Snoek,Alex Wiltschko

主题演讲:Fei-Fei Li

 

•2017年NIPS系列研讨会

https://nips.cc/Conferences/2017/Schedule?showEvent=8750

组织者包括:Vitaly Kuznetsov

作者包括:Brendan Jou

 

•OPT 2017:机器学习的优化

https://nips.cc/Conferences/2017/Schedule?showEvent=8771

主办单位包括:Sashank Reddi

 

•机器学习系统研讨会

https://nips.cc/Conferences/2017/Schedule?showEvent=8774

邀请演讲嘉宾包括:Rajat Monga、Alexander Mordvintsev、Chris Olah、Jeff Dean

作者包括:Alex Beutel、Tim Kraska、Ed H. Chi、D. Scully、Michael Terry

 

•均衡的人工智能Aligned Artificial Intelligence

https://nips.cc/Conferences/2017/Schedule?showEvent=8794

特邀演讲嘉宾包括:Ian Goodfellow

 

•贝叶斯深度学习

Bayesian Deep Learning

https://nips.cc/Conferences/2017/Schedule?showEvent=8753

主办单位包括:Kevin Murphy

特邀演讲嘉宾包括:Nal Kalchbrenner、Matthew D. Hoffman

 

•BigNeuro 2017

https://nips.cc/Conferences/2017/Schedule?showEvent=8780

特邀演讲嘉宾包括:Viren Jain

 

•认知人工智能:来自自然智能的见解Cognitively Informed Artificial Intelligence: Insights From NaturalIntelligence

https://nips.cc/Conferences/2017/Schedule?showEvent=8765

作者包括:Jiazhong Nie、Ni Lao

 

•超级计算机规模领域的深度学习

https://nips.cc/Conferences/2017/Schedule?showEvent=8793

主办单位包括:Erich Elsen,Zak Stone、Brennan Saeta、Danijar Haffner

 

•深度学习:连接理论与实践的桥梁

https://nips.cc/Conferences/2017/Schedule?showEvent=8776

特邀演讲嘉宾包括:Ian Goodfellow

 

•深度学习的可解释性、理解性和可视化

https://nips.cc/Conferences/2017/Schedule?showEvent=8795

特邀演讲嘉宾包括:Kim、Honglak Lee

作者包括:Pieter Kinderman、Sara Hooker、Dumitru Erhan、Been Kim

 

•学习解构特征:从感知到控制

https://nips.cc/Conferences/2017/Schedule?showEvent=8787

主办方包括:Honglak Lee

作者包括:Jasmine Hsu、Arkanath Pathak、Abhinav Gupta、James Davidson、Honglak Lee

 

•学习有限的标记数据:弱监督及其超越

https://nips.cc/Conferences/2017/Schedule?showEvent=9478

特邀演讲嘉宾包括:Ian Goodfellow

 

•在电话和其他消费者设备领域的机器学习

https://nips.cc/Conferences/2017/Schedule?showEvent=8791

特邀演讲嘉宾包括:Rajat Monga

组织者包括:Hrishikesh Aradhye

作者包括Suyog Gupta、Sujith Ravi

 

•最有传输和机器学习Optimal Transport and Machine Learning

https://nips.cc/Conferences/2017/Schedule?showEvent=8758

主办单位包括:Olivier Bousquet

 

•基于梯度的机器学习软件和技术的未来发展

https://nips.cc/Conferences/2017/Schedule?showEvent=8779

主办方包括:Alex Wiltschko、Bart vanMerriënboer

 

•元学习研讨会

https://nips.cc/Conferences/2017/Schedule?showEvent=8767

主办单位包括:Hugo Larochelle

小组成员包括:Samy Bengio

作者包括:Aliaksei Severyn、Sascha Rothe

 

专题讨论会


•深度强化学习研讨会

https://nips.cc/Conferences/2017/Schedule?showEvent=8743

作者包括:Benjamin Eysenbach、Shane Gu、Julian Ibarz、Sergey Levine

 

•可解释性机器学习

https://nips.cc/Conferences/2017/Schedule?showEvent=8744

作者包括:Minmin Chen

 

•元学习(Metalearning)

https://nips.cc/Conferences/2017/Schedule?showEvent=8746

主办方包括:Quoc V Le

 

竞赛


•对抗式攻击和防御

https://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack

主办方包括:Alexey Kurakin、Ian Goodfellow、Samy Bengio

 

•竞争IV:临床可操作的基因突变分类

https://www.kaggle.com/c/msk-redefining-cancer-treatment

主办单位包括:Wendy Kan

 

教程

 

•机器学习的公平性

https://nips.cc/Conferences/2017/Schedule?showEvent=8734

Solon Barocas、 Moritz Hardt


 欢迎个人分享,媒体转载请后台回复「转载」获得授权,微信搜索「BOBO_AI」关注公众号


中国人工智能产业创新联盟于2017年6月21日成立,超200家成员共推AI发展,相关动态:

中新网:中国人工智能产业创新联盟成立

ChinaDaily:China forms 1st AI alliance

证券时报:中国人工智能产业创新联盟成立 启动四大工程搭建产业生态“梁柱”

工信部网站:中国人工智能产业创新联盟与贵阳市政府、英特尔签署战略合作备忘录


点击下图加入联盟


下载中国人工智能产业创新联盟入盟申请表


关注“雷克世界”后不要忘记置顶

我们还在搜狐新闻、雷克世界官网、腾讯新闻、网易新闻、一点资讯、天天快报、今日头条、雪球财经……

↓↓↓点击阅读原文查看中国人工智能产业创新联盟手册

您可能也对以下帖子感兴趣

文章有问题?点此查看未经处理的缓存