雷锋网AI科技评论按:NIPS 2017 将于 12 月份在美国长滩举行,本届NIPS共收到 3240 篇论文投稿,录用 678 篇,录用率为 20.9%;其中包括 40 篇口头报告论文和 112 篇 spotlight 论文。详细录用名单日前已经公布,可参见:https://nips.cc/Conferences/2017/AcceptedPapersInitial
为方便浏览全貌,雷锋网AI科技评论为读者整理了多家高校及企业的录用名单。
先来看看国内高校情况。国人心目中科研实力最强的清华大学,今年共有6篇录用论文,包括张钹院士、王建民博士、鲁继文博士、朱军博士都有论文被录用;而北京大学也表现不俗,有四篇论文被录用。此外,包括中国科学院、中国科学技术大学、香港科技大学、香港中文大学及香港城市大学在内的多家高校也有多篇论文中了NIPS。由于论文可能涉及多位合作者,因此以下的名单均以第一作者所属机构为准。
PredRNN: Recurrent Neural Networks for Video Prediction using Spatiotemporal LSTMs
Yunbo Wang (Tsinghua University) · Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University) · Philip S Yu (UIC)
Learning Multiple Tasks with Deep Relationship Networks
Mingsheng Long (Tsinghua University) · Jianmin Wang (Tsinghua University) · Philip S Yu (UIC)
Runtime Neural Pruning
Ji Lin (Tsinghua University) · Yongming Rao (Tsinghua University) · Jiwen Lu (Tsinghua University)
Triple Generative Adversarial Nets
Chongxuan LI (Tsinghua University) · Kun Xu () · Jun Zhu (Tsinghua University) · Bo Zhang (Tsinghua University)
Accelerated Stochastic Greedy Coordinate Descent by Soft Thresholding Projection onto Simplex
Chaobing Song (Tsinghua University) · Shaobo Cui (Tsinghua University) · Shu-Tao Xia (Tsinghua University) · Yong Jiang (Tsinghua-Berkeley Shenzhen Institute)
Population Matching Discrepancy and Applications in Deep Learning
Jianfei Chen (Tsinghua University) · Chongxuan LI (Tsinghua University) · Yizhong Ru (Tsinghua University) · Jun Zhu (Tsinghua University)
Deep Dynamic Poisson Factorization Model
Chengyue Gong (PeKing University) • win-bin huang (peking university)
Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
Cong Fang (Peking University) · Feng Cheng (Peking University) · Zhouchen Lin (Peking University)
From Bayesian Sparsity to Gated Recurrent Nets
Hao He (PekingUniversity) · Bo Xin (Microsoft Research) · David Wipf (Microsoft Research)
The Expressive Power of Neural Networks: A View from the Width
Zhou Lu (Peking University) · Hongming Pu (Peking university) · Feicheng Wang (Peking University) · Zhiqiang Hu (Peking University) · Liwei Wang (Peking University)
Deep supervised discrete hashing
Qi Li (Institute of Automation, Chinese Academy of Sciences) · Zhenan Sun () · Ran He (CASIA) · Tieniu Tan (Chinese Academy of Sciences)
Deliberation Networks: Sequence Generation Beyond One-Pass Decoding
Yingce Xia (University of Science and Technology of China) · Lijun Wu (Sun Yat-sen University) · Jianxin Lin (USTC) · Fei Tian (Miicrosoft Research) · Tao Qin (Microsoft Research) · Tie-Yan Liu (Microsoft Research)
Subset Selection under Noise
Chao Qian (University of Science and Technology of China) · Jing-Cheng Shi (Nanjing University) · Yang Yu () · Ke Tang (University of Science and Technology of China) · Zhi-Hua Zhou (Nanjing University)
Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
Yu Liu (The Chinese University of Hong Kong) · Hongyang Li (The Chinese University of Hong Kong) · Xiaogang Wang (The Chinese University of Hong Kong)
Contrastive Learning for Image Captioning
Bo Dai (The Chinese University of Hong Kong) · Dahua Lin (The Chinese University of Hong Kong)
Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds
Yuanyuan Liu (The Chinese University of Hong Kong) · Fanhua Shang (The Chinese University of Hong Kong) · James Cheng (The Chinese University of Hong Kong) · Hong Cheng (The Chinese University of Hong Kong) · Licheng Jiao (Xidian University)
Geometric Descent Method for Convex Composite Minimization
Shixiang Chen (The Chinese University of HongKong) · Shiqian Ma (UC Davis) · Wei Liu (Tencent Technology (Shenzhen) Company Limited)
Incorporating Side Information by Adaptive Convolution
Di Kang (City University of Hong Kong) · Debarun Dhar (City University of Hong Kong) · Antoni Chan (City University of Hong Kong)
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
Xingjian Shi (HKUST) · Hao Wang (HKUST) · Zhihan Gao (HKUST) · Leonard Lausen (HKUST) · Dit-Yan Yeung (HKUST, Hong Kong) · Wang-chun WOO (HKO) · Wai-kin Wong (HKO)
自 1987 年到 2000 年,NIPS都在美国丹佛举办,虽然后来也曾经在加拿大温哥华、西班牙的格兰纳达、加拿大蒙特利尔举办,但不得不承认的是,美国一直是全球科研的主要阵地。今年NIPS上,美国计算机四大名校(CMU、MIT、UC伯克利、斯坦福)“理所当然”地霸屏,仅以第一作者所属机构统计的录用论文就达92篇(有一篇是第一作者隶属双院校的),其中 CMU 37篇,成为今年最大赢家;MIT和斯坦福各有20篇论文,UC伯克利有16篇论文被录用。
由于正文篇幅有限,关注“AI科技评论”(aitechtalk)后,回复“美国名校NIPS”可查看四大名校论文完整名单。
再和雷锋网AI科技评论一起来看看国内BAT三家的论文录用情况。今年NIPS上,尚未看到阿里被录用的论文,腾讯有一篇作为第一作者的录用论文,另有两篇为合作论文;而百度美研院今年有一篇关于Deep Voice2的论文被收录;截至目前,尚未看到阿里的相关录用论文。
Mixture-Rank Matrix Approximation for Collaborative Filtering
Dongsheng Li (IBM Research - China) · Chao Chen (Tongji University) · Wei Liu (Tencent Technology (Shenzhen) Company Limited) · Tun Lu (Fudan University) · Ning Gu (Fudan University) · Stephen Chu (IBM Research - China)
Geometric Descent Method for Convex Composite Minimization
Shixiang Chen (The Chinese University of HongKong) · Shiqian Ma (UC Davis) · Wei Liu (Tencent Technology (Shenzhen) Company Limited)
Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding
Wenbing Huang (Tencent AI Lab) · Fuchun Sun (Tsinghua University) · Tong Zhang (The Australian National University) · Junzhou Huang (University of Texas at Arlington) · Mehrtash Harandi (Data61)
Deep Voice 2: Multi-Speaker Neural Text-to-Speech
Andrew Gibiansky (Baidu Research)
最后再看看其它国际研究院/企业的表现。惊喜之外意料之中的是,微软研究院共有16篇第一作者论文被录用,包括此前雷锋网AI科技评论报道提及的,微软亚洲研究院的4篇文章。谷歌今年有7篇论文上榜,OpenAI,Facebook也表现不俗。
往期报道可参阅:https://www.leiphone.com/news/201709/BiZ4ytOqR0LOHZnN.html
Decoding with Value Networks for Neural Machine Translation
Di He (Microsoft Research) · Hanqing Lu (Zhejiang University) · Yingce Xia (University of Science and Technology of China) · Tao Qin (Microsoft Research) · Liwei Wang (Peking University) · Tieyan Liu (Microsoft Research)
Inference in Graphical Models via Semidefinite Programming Hierarchies
Murat Erdogdu (Microsoft Research) · Yash Deshpande (MIT) · Andrea Montanari (Stanford)
Neural Program Meta-Induction
Jacob Devlin (Microsoft Research) · Rudy R Bunel (Oxford University) · Rishabh Singh (Microsoft Research) · Matthew Hausknecht (Microsoft Research) · Pushmeet Kohli (DeepMind)
Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM
Steven Wu (Microsoft Research) · Bo Waggoner () · Seth Neel (University of Pennsylvania) · Aaron Roth (University of Pennsylvania) · Katrina Ligett ()
A Highly Efficient Gradient Boosting Decision Tree
Guolin Ke (Microsoft Research) · Qi Meng (Peking University) · Taifeng Wang (Microsoft Research) · Wei Chen (Microsoft Research Asia) · Weidong Ma (Microsoft Research) · Tie-Yan Liu (Microsoft Research)
Clustering Billions of Reads for DNA Data Storage
Cyrus Rashtchian (University of Washington) · Konstantin Makarychev (Microsoft) · Luis Ceze (Microsoft) · Karin Strauss (Microsoft Research) · Sergey Yekhanin (Microsoft) · Djordje Jevdjic (Microsoft Research) · Miklos Racz (Princeton University) · Siena Ang (Microsoft)
Collecting Telemetry Data Privately
Bolin Ding (Microsoft) · Janardhan Kulkarni (Microsoft Research) · Sergey Yekhanin (Microsoft)
Off-policy evaluation for slate recommendation
Adith Swaminathan (Microsoft Research) · Akshay Krishnamurthy () · Alekh Agarwal (Microsoft Research) · Miro Dudik (Microsoft Research) · John Langford (Microsoft Research) · Damien Jose (Microsoft) · Imed Zitouni (Microsoft)
A Decomposition of Forecast Error in Prediction Markets
Miro Dudik (Microsoft Research) · Sebastien Lahaie (Google) · Ryan M Rogers (University of Pennsylvania) · Jennifer Wortman Vaughan (Microsoft Research)
Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation
Christian Borgs (Microsoft Research New England) · Jennifer Chayes (Microsoft Research) · Christina Lee (MIT) · Devavrat Shah (Massachusetts Institute of Technology)
Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
Jianshu Chen (Microsoft Research, Redmond, W) · Chong Wang () · Lin Xiao (Microsoft Research) · Ji He (University Washington) · Lihong Li (Microsoft Research) · Li Deng (Citadel)
Online Learning with a Hint
Ofer Dekel (Microsoft Research) · arthur flajolet (MIT) · Nika Haghtalab (Carnegie Mellon University) · Patrick Jaillet (Massachusetts Institute of Technology)
A Sample Complexity Measure with Applications to Learning Optimal Auctions
Vasilis Syrgkanis (Microsoft Research)
Hybrid Reward Architecture for Reinforcement Learning
Harm Van Seijen (Microsoft Research) · Romain Laroche () · Mehdi Fatemi () · Joshua Romoff (McGill University)
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls
Zeyuan Allen-Zhu (Microsoft Research) · Elad Hazan (Princeton University) · Wei Hu (Princeton University) · Yuanzhi Li (Princeton University)
Z-Forcing: Training Stochastic Recurrent Networks
Marc-Alexandre Côté (Microsoft Maluuba) · Alessandro Sordoni (Microsoft Maluuba) · Anirudh Goyal ALIAS PARTH GOYAL (Université de Montréal) · Nan Ke (MILA, École Polytechnique de Montréal) · Yoshua Bengio (U. Montreal)
On the Consistency of Quick Shift
Heinrich Jiang (Google)
Attention is All you Need
Ashish Vaswani (Google Brain) · Noam Shazeer (Google) · Niki Parmar (Google) · Llion Jones (Google) · Jakob Uszkoreit (Google, Inc.) · Aidan N Gomez (University of Toronto) · Łukasz Kaiser (Google Brain)
雷锋网AI科技评论往期报道:https://www.leiphone.com/news/201706/H2PUINRPl9XKrC1R.html
Parameter-Free Online Learning via Model Selection
Dylan J Foster (Cornell University) · Satyen Kale (Google) · Mehryar Mohri (Courant Institute and Google) · Karthik Sridharan (Cornell University)
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Understanding and Improvement
Maithra Raghu (Cornell University and Google Brain) · Justin Gilmer (Google Brain) · Jason Yosinski (Uber) · Jascha Sohl-Dickstein (Google Brain)
Neural Discrete Representation Learning
Aaron van den Oord (Google Deepmind) · Oriol Vinyals (Google DeepMind) · koray kavukcuoglu (DeepMind)
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Balaji Lakshminarayanan (Google Deepmind) · Alexander Pritzel (Google Deepmind) · Charles Blundell (DeepMind)
Acceleration and Averaging in Stochastic Descent Dynamics
Walid Krichene (Google)
Deep Reinforcement Learning from Human Preferences
Paul F Christiano (OpenAI) · Jan Leike (DeepMind) · Tom Brown (OpenAI) · Miljan Martic (DeepMind) · Shane Legg (DeepMind) · Dario Amodei (OpenAI)
Hindsight Experience Replay
Marcin Andrychowicz (OpenAI) · Filip Wolski (OpenAI) · Alex Ray (OpenAI) · Jonas Schneider (OpenAI) · Rachel Fong (OpenAI) · Peter Welinder (OpenAI) · Bob McGrew (OpenAI) · Josh Tobin (OpenAI) · OpenAI Pieter Abbeel (OpenAI, UC Berkeley) · Wojciech Zaremba (OpenAI)
Hierarchical Implicit Models and Likelihood-Free Variational Inference
Dustin Tran (Columbia University & OpenAI) · Rajesh Ranganath (Princeton University) · David Blei (Columbia University)
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Yuandong Tian (Facebook AI Research) · Qucheng Gong (Facebook AI Research) · Wenling Shang (435024885627) · Yuxin Wu (Facebook AI Research) · C. Lawrence Zitnick (Facebook AI Research)
雷锋网AI科技评论往期报道:https://www.leiphone.com/news/201709/aZ33T276udayVdjz.html
Multi-agent Predictive Modeling with Attentional CommNets
Yedid Hoshen (Facebook AI Research)
Fader Networks: Generating Image Variations by Sliding Attribute Values
Guillaume Lample (Facebook AI Research) · Neil Zeghidour (Facebook A.I. Research / Ecole Normale Supérieure) · Nicolas Usunier (Facebook AI Research) · Antoine Bordes (Facebook AI Research) · Ludovic DENOYER (Universite Pierre et Marie Curie - Paris) · Marc'Aurelio Ranzato (Facebook)
Poincaré Embeddings for Learning Hierarchical Representations
Maximillian Nickel (Facebook) · Douwe Kiela (Facebook AI Research)
Gradient Episodic Memory for Continuum Learning
David Lopez-Paz (Facebook AI Research) · Marc'Aurelio Ranzato (Facebook)
Houdini: Democratizing Adversarial Examples
Moustapha Cisse (Facebook AI Research) · Yossi Adi (Bar Ilan University) · Natalia Neverova (Facebook AI Research) · Joseph Keshet (Bar-Ilan University)
更多资讯敬请关注雷锋网AI科技评论。