NIPS 2017美国四大名校霸屏，92篇论文抢先看 | NIPS 2017

雷锋网AI科技评论按：NIPS 2017将于今年12月在美国长滩举办。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。

近日，雷锋网AI科技评论发现NIPS录用结果已经出炉。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，雷锋网(公众号：雷锋网)AI科技评论统计了详细名单，整理如下（统计中排除了一篇双机构的）：

CMU，37篇

• Attentional Pooling for Action Recognition

  Rohit Girdhar (Carnegie Mellon University) · Deva Ramanan (Carnegie Mellon University)

• On the Power of Truncated SVD for General High-rank Matrix Estimation Problems

  Simon Du (Carnegie Mellon University) · Yining Wang (Carnegie Mellon University) · Aarti Singh (CMU)

• Dykstra's Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions

  Ryan J Tibshirani (Carnegie Mellon University)

• Hypothesis Transfer Learning via Transformation Functions

  Simon Du (Carnegie Mellon University) · Jayanth Koushik (Carnegie Mellon University) · Aarti Singh (CMU) · Barnabas Poczos (Carnegie Mellon University) 

• Adversarial Invariant Feature Learning

  Qizhe Xie (Carnegie Mellon University) · Zihang Dai (CMU) · Yulun Du (CMU) · Eduard Hovy (CMU) · Graham Neubig (Carnegie Mellon University)

• Safe and Nested Subgame Solving for Imperfect-Information Games

  Noam Brown (Carnegie Mellon University) · Tuomas Sandholm (Carnegie Mellon University)

• Coded Distributed Computing for Inverse Problems

  Yaoqing Yang (Carnegie Mellon University) · Pulkit Grover (CMU) · Soummya Kar (Carnegie Mellon University)

• Gradient Descent Can Take Exponential Time to Escape Saddle Points

  Simon Du (Carnegie Mellon University) · Chi Jin (UC Berkeley) · Jason D Lee (USC) · Michael Jordan (UC Berkeley) · Aarti Singh (CMU) · Barnabas Poczos (Carnegie Mellon University)

• Predictive-State Decoders: Encoding the Future into Recurrent Networks

  Arun Venkatraman (Carnegie Mellon University) · Nicholas Rhinehart (Carnegie Mellon University) · Wen Sun (Carnegie Mellon University) · Lerrel Pinto () · Martial Hebert (cmu) · Byron Boots (Georgia Tech / Google Brain) · Kris Kitani (Carnegie Mellon University) · J. Bagnell (Carnegie Mellon University)

• Deanonymization in the Bitcoin P2P Network

  Giulia Fanti (Carnegie Mellon University) · Pramod Viswanath (UIUC)

• Adaptive sampling for a population of neurons

  Benjamin Cowley (Carnegie Mellon University) · Ryan Williamson (Carnegie Mellon University) · Katerina Clemens (University of Pittsburgh) · Matthew Smith (University of Pittsburgh) · Byron M Yu (Carnegie Mellon University)

• Max-Margin Invariant Features from Transformed Unlabelled Data

  Dipan Pal (Carnegie Mellon University) · Ashwin Kannan (Carnegie Mellon University) · Gautam Arakalgud (Carnegie Mellon University) · Marios Savvides (Carnegie Mellon University)

• MMD GAN: Towards Deeper Understanding of Moment Matching Network

  Chun-Liang Li (Carnegie Mellon University) · Wei-Cheng Chang (Carnegie Mellon University) · Yu Cheng (AI Foundations, IBM Research) · Yiming Yang (CMU) · Barnabas Poczos (Carnegie Mellon University)

• Differentiable Learning of Logical Rules for Knowledge Base Reasoning

  Fan Yang (Carnegie Mellon University) · Zhilin Yang (Carnegie Mellon University) · William W Cohen (Carnegie Mellon University)

• Collaborative PAC Learning

  Avrim Blum (CMU) · Nika Haghtalab (Carnegie Mellon University) · Ariel D Procaccia (Carnegie Mellon University) · IIIS Mingda Qiao (IIIS, Tsinghua University)

• Noise-Tolerant Interactive Learning Using Pairwise Comparisons

  Yichong Xu (Carnegie Mellon University) · Hongyang Zhang (Carnegie Mellon University) · Aarti Singh (Carnegie Mellon University) · Artur Dubrawski (Carnegie Mellon University) · Kyle Miller (Carnegie Mellon University)

• Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation

  Zhaohan Guo (Carnegie Mellon University/Stanford) · Philip S. Thomas (CMU) · Emma Brunskill (CMU)

• Deep Sets

  Manzil Zaheer (Carnegie Mellon University) · Satwik Kottur (Carnegie Mellon University) · Siamak Ravanbakhsh (CMU/UBC) · Barnabas Poczos (Carnegie Mellon University) · Ruslan Salakhutdinov () · Alexander Smola (Amazon – We are hiring!)

• Structured Generative Adversarial Networks

  Hao Zhang (Carnegie Mellon University) · Zhijie Deng (Tsinghua University) · Xiaodan Liang (Carnegie Mellon University) · Jun Zhu (Tsinghua University) · Eric P Xing (Carnegie Mellon University)

• On-the-fly Operation Batching in Dynamic Computation Graphs

  Graham Neubig (Carnegie Mellon University) · Yoav Goldberg (Bar-Ilan University) · Chris Dyer (DeepMind)

• Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach

  Emmanouil Platanios (Carnegie Mellon University) · Hoifung Poon (Microsoft Research) · Tom M Mitchell (Carnegie Mellon University) · Eric J Horvitz (Microsoft Research)

• The Expxorcist: Nonparametric Graphical Models Via Conditional Exponential Densities

  Arun Suggala (Carnegie Mellon University) · Mladen Kolar (University of Chicago) · Pradeep Ravikumar (Carnegie Mellon University)

• Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs

  Sanjiban Choudhury (Carnegie Mellon University) · Shervin Javdani (Carnegie Mellon University) · Siddhartha Srinivasa (Carnegie Mellon University) · Sebastian Scherer (Carnegie Mellon University)

• Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions

  Maria-Florina Balcan (Carnegie Mellon University) · Hongyang Zhang (Carnegie Mellon University)

• Self-supervised Learning of Motion Capture

  Hsiao-Yu Tung (Carnegie Mellon University) · Hsiao-Wei Tung (University of Pittsburgh) · Ersin Yumer (Adobe Research) · Katerina Fragkiadaki ()

• Task-based End-to-end Model Learning in Stochastic Optimization

  Priya Donti (Carnegie Mellon University) · J. Zico Kolter (Carnegie Mellon University) · Brandon Amos (Carnegie Mellon University)

• Gradient descent GAN optimization is locally stable

  Vaishnavh Nagarajan (Carnegie Mellon University) · J. Zico Kolter (Carnegie Mellon University)

• Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

  Christoph Dann (Carnegie Mellon University) · Tor Lattimore (DeepMind) · Emma Brunskill (Stanford University)

• Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods

  Veeranjaneyulu Sadhanala (CMU) · Yu-Xiang Wang (CMU / Amazon AI) · James Sharpnack () · Ryan J Tibshirani (Carnegie Mellon University)

• Predictive State Recurrent Neural Networks

  Carlton Downey (Carnegie Mellon University) · Ahmed Hefny (Carnegie Mellon University) · Byron Boots (Georgia Tech / Google Brain) · Geoffrey Gordon (CMU) · Boyue Li (Carnegie Mellon University)

• Predictive State Recurrent Neural Networks

  Carlton Downey (Carnegie Mellon University) · Ahmed Hefny (Carnegie Mellon University) · Byron Boots (Georgia Tech / Google Brain) · Geoffrey Gordon (CMU) · Boyue Li (Carnegie Mellon University)

• Good Semi-supervised Learning That Requires a Bad GAN

  Zihang Dai (Carnegie Mellon University) · Zhilin Yang (Carnegie Mellon University) · Fan Yang (Carnegie Mellon University) · William W Cohen (Carnegie Mellon University) · Ruslan Salakhutdinov ()

• A Sharp Error Analysis for the Fused Lasso, with Implications to Broader Settings and Approximate Screening

  Kevin Lin (Carnegie Mellon University) · James Sharpnack () · Alessandro Rinaldo (CMU) · Ryan Tibshirani (Carnegie Mellon University)

• Efficient Computation of Moments in Sum-Product Networks

  Han Zhao (Carnegie Mellon University)

• Active Learning from Peers

  Keerthiram Murugesan (Carnegie Mellon University) · Jaime Carbonell (CMU)

• Learning to Model the Tail

  Yu-Xiong Wang (Carnegie Mellon University) · Deva Ramanan (Carnegie Mellon University) · Martial Hebert (cmu)

• On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models

  Adarsh Prasad (Carnegie Mellon University) · Pradeep Ravikumar (Carnegie Mellon University)

MIT，20篇

• Concentration of Multilinear Functions of the Ising Model with Applications to Network Data

  Constantinos Daskalakis (MIT) · Nishanth Dikkala (MIT) · Gautam Kamath (MIT)

• Scene Physics Acquisition via Visual De-animation

  Jiajun Wu (MIT) · Erika Lu (University of Oxford) · Pushmeet Kohli (DeepMind) · Bill Freeman (MIT/Google) · Josh Tenenbaum (MIT)

• 3D Shape Reconstruction by Modeling 2.5D Sketch

  Jiajun Wu (MIT) · Yifan Wang (ShanghaiTech University) · Tianfan Xue (MIT CSAIL) · Xingyuan Sun (Shanghai Jiao Tong University) · Bill Freeman (MIT/Google) · Josh Tenenbaum (MIT)

• Shape and Material from Sound

  zhoutong zhang (MIT) · Qiujia Li (University of Cambridge) · Zhengjia Huang () · Jiajun Wu (MIT) · Josh Tenenbaum (MIT) · Bill Freeman (MIT/Google)

• Lookahead Bayesian Optimization with Inequality Constraints

  Remi Lam (MIT) · Karen Willcox (MIT)

• Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration

  Jason Altschuler (MIT) · Jonathan Weed (MIT) · Philippe Rigollet (MIT)

• Elementary Symmetric Polynomials for Optimal Experimental Design

  Zelda E. Mariet (MIT) · Suvrit Sra (MIT)

• Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems

  Yonatan Belinkov (MIT)

• Information Theoretic Properties of Markov Random Fields, and their Algorithmic Applications

  Linus Hamilton (MIT) · Frederic Koehler (MIT) · Ankur Moitra ()

• Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

  Wengong Jin (MIT CSAIL) · Connor W Coley (MIT Department of Chemical Engineering) · Regina Barzilay (Massachusetts Institute of Technology) · Tommi Jaakkola (MIT)

• Practical Data-Dependent Metric Compression with Provable Guarantees

  Piotr Indyk (MIT) · Ilya Razenshteyn (Columbia University) · Tal Wagner (MIT)

• Parallel Streaming Wasserstein Barycenters

  Matthew Staib (MIT) · Sebastian Claici (MIT) · Justin M Solomon (MIT) · Stefanie Jegelka (MIT)

• On Optimal Generalizability in Parametric Learning

  Ahmad Beirami (Harvard University & MIT) · Meisam Razaviyayn (University of Southern California) · Shahin Shahrampour (Harvard University) · Vahid Tarokh (Harvard University) On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks

• On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks

  Arturs Backurs (MIT) · Piotr Indyk (MIT) · Ludwig Schmidt (MIT)

• Polynomial time algorithms for dual volume sampling

  Chengtao Li (MIT) · Stefanie Jegelka (MIT) · Suvrit Sra (MIT)

• Real-Time Bidding with Side Information

  arthur flajolet (MIT) · Patrick Jaillet (Massachusetts Institute of Technology)

• Local Aggregative Games

  Vikas Garg (MIT) · Tommi Jaakkola (MIT)

• Permutation-based Causal Inference Algorithms with Interventions

  Yuhao Wang (MIT) · Liam Solus (KTH Royal Institute of Technology) · Karren Yang (MIT) · Caroline Uhler (MIT)

• Learning to Generalize Intrinsic Images with a Structured Disentangling Autoencoder

  Michael Janner (MIT) · Jiajun Wu (MIT) · Tejas Kulkarni (DeepMind) · Ilker Yildirim (MIT) · Josh Tenenbaum (MIT)

• Style Transfer from Non-parallel Text by Cross-Alignment

  Tianxiao Shen (MIT) · Tao Lei (MIT) · Regina Barzilay (Massachusetts Institute of Technology) · Tommi Jaakkola (MIT)

UC伯克利，16篇

• Learning a Multi-View Stereo Machine

  Abhishek Kar (UC Berkeley) · Jitendra Malik () · Christian Häne (UC Berkeley)

• Multimodal Image-to-Image Translation by Enforcing Bi-Cycle Consistency

  Jun-Yan Zhu (UC Berkeley) · Richard Zhang (University of California, Berkeley) · Deepak Pathak (UC Berkeley) · Trevor Darrell (UC Berkeley) · Oliver Wang (Adobe Research) · Eli Shechtman () · Alexei Efros (UC Berkeley)

• One-Shot Imitation Learning

  Yan Duan (UC Berkeley) · Marcin Andrychowicz (OpenAI) · Bradly Stadie (OpenAI) · OpenAI Jonathan Ho (OpenAI, UC Berkeley) · Jonas Schneider (OpenAI) · Ilya Sutskever () · Pieter Abbeel (OpenAI / UC Berkeley / Gradescope) · Wojciech Zaremba (OpenAI)

• Fast Alternating Minimization Algorithms for Dictionary Learning

  Niladri Chatterji (UC Berkeley) · Peter Bartlett (UC Berkeley)

• Consistent Robust Regression

  Kush Bhatia (UC Berkeley) · Prateek Jain (Microsoft Research) · Purushottam Kar (Indian Institute of Technology Kanpur)

• Non-convex Finite-Sum Optimization Via SCSG Methods

  Lihua Lei (UC Berkeley) · Cheng Ju (University of California, Berkeley) · Jianbo Chen (University of California, Berkeley) · Michael Jordan (UC Berkeley)

• Fast Black-box Variational Inference through Stochastic Trust-Region Optimization

  Jeffrey Regier (UC Berkeley) · Michael Jordan (UC Berkeley) · Jon McAuliffe (UC Berkeley)

• Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems

  Alyson Fletcher (UCLA, UCSC, & UC Berkeley) · Sundeep Rangan (NYU-Poly) · Mojtaba Sahraee-Ardakan (UCLA) · Philip Schniter (Ohio State University)

• EX2: Exploration with Exemplar Models for Deep Reinforcement Learning

  Justin Fu (UC Berkeley) · John Co-Reyes (UC Berkeley) · Sergey Levine (UC Berkeley)

• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

  Haoran Tang (UC Berkeley) · Pieter Abbeel (OpenAI / UC Berkeley / Gradescope) · Davis J Foote (UC Berkeley) · Yan Duan () · OpenAI Xi Chen (OpenAI, UC Berkeley) · Rein Houthooft (OpenAI) · Adam Stooke (UC Berkeley) · Filip DeTurck

• Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach

  Roel Dobbe (UC Berkeley) · David Fridovich-Keil (UC Berkeley) · Claire Tomlin (UC Berkeley)

• The Marginal Value of Adaptive Gradient Methods in Machine Learning

  Ashia C Wilson (UC Berkeley) · Rebecca D Roelofs (UC Berkeley) · Mitchell Stern (UC Berkeley) · Nati Srebro (TTI-Chicago) · Benjamin Recht (UC Berkeley)

• Federated Multi-Task Learning

  Virginia Smith (UC Berkeley) · Maziar Sanjabi (University of California, Los Angeles) · Chao-Kai Chiang (University of Southern California) · Ameet S Talwalkar (UCLA)

• Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities

  Michael Eickenberg (UC Berkeley) · Georgios Exarchakis (Ecole Normale Supérieure) · Matthew Hirn (Michigan State University) · Stephane Mallat (Ecole normale superieure)

• Inverse Reward Design

  Dylan Hadfield-Menell (UC Berkeley) · Smitha Milli (UC Berkeley) · Stuart J Russell (UC Berkeley) · Pieter Abbeel (OpenAI / UC Berkeley / Gradescope) · Anca Dragan (UC Berkeley)

• Kernel Feature Selection via Conditional Covariance Minimization

  Jianbo Chen (University of California, Berkeley) · Mitchell Stern (UC Berkeley) · Martin J Wainwright (UC Berkeley) · Michael Jordan (UC Berkeley)

斯坦福，20篇

• Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation

  Zhaohan Guo (Carnegie Mellon University/Stanford) · Philip S. Thomas (CMU) · Emma Brunskill (CMU)

• Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System

  Chengxu Zhuang (Stanford University) · Jonas Kubilius (Massachusetts Institute of Technology) · Mitra JZ Hartmann (Northwestern University) · Daniel Yamins (Stanford University)

• Robust Estimation of Neural Signals in Calcium Imaging

  Hakan Inan (Stanford University) · Murat Erdogdu (Microsoft Research) · Mark Schnitzer (Stanford University)

• Variance-based Regularization with Convex Objectives

  Hongseok Namkoong (Stanford University) · John C Duchi (Stanford)

• Variance-based Regularization with Convex Objectives

  Hongseok Namkoong (Stanford University) · John C Duchi (Stanford)

• An Applied Algorithmic Foundation for Hierarchical Clustering

  Joshua Wang (Stanford University) · Benjamin Moseley (Washington University in St Lo)

• Learning to Compose Domain-Specific Transformations for Data Augmentation

  Alexander Ratner (Stanford) · Henry Ehrenberg (Stanford University) · Zeshan Hussain (Stanford University) · Jared Dunnmon (Stanford University) · Christopher Ré (Stanford)

• Ensemble Sampling

  Xiuyuan Lu (Stanford University) · Benjamin Van Roy (Stanford University)

• Language modeling with recurrent highway hypernetworks

  Joseph Suarez (Stanford University)

• Certified Defenses for Data Poisoning Attacks

  Jacob Steinhardt (Stanford University) · Pang Wei W Koh (Stanford University) · Percy S Liang (Stanford University)

• Conservative Contextual Linear Bandits

  Abbas Kazerouni (Stanford University) · Mohammad Ghavamzadeh (DeepMind) · Yasin Abbasi (Adobe Research) · Benjamin Van Roy (Stanford University)

• Stochastic and Adversarial Online Learning without Hyperparameters

  Ashok Cutkosky (Stanford University) · Kwabena A Boahen (Stanford University)

• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

  Charles Ruizhongtai Qi (Stanford University) · Li Yi (Stanford University) · Hao Su (Stanford) · Leonidas J Guibas (stanford.edu)

• A-NICE-MC: Adversarial Training for MCMC

  Jiaming Song (Stanford University) · Shengjia Zhao (Stanford University) · Stefano Ermon (Stanford)

• Optimally Learning Populations of Parameters

  Kevin Tian (Stanford University) · Weihao Kong (Stanford University) · Gregory Valiant (Stanford University)

• Gaussian Quadrature for Kernel Features

  Tri Dao (Stanford University) · Christopher M De Sa (Stanford) · Christopher Ré (Stanford)

• Delayed Mirror Descent in Continuous Games

  Zhengyuan Zhou (Stanford University) · Panayotis Mertikopoulos () · Nicholas Bambos () · Peter W Glynn (Stanford University) · Claire Tomlin (UC Berkeley)

• Learning Mixture of Gaussians with Streaming Data

  Aditi Raghunathan (Stanford University) · Prateek Jain (Microsoft Research) · Ravishankar Krishnawamy (Microsoft Research India)

• Neural Variational Inference and Learning in Undirected Graphical Models

  Volodymyr Kuleshov (Stanford University) · Stefano Ermon (Stanford)

• Stochastic Mirror Descent for Non-Convex Optimization

  Zhengyuan Zhou (Stanford University) · Panayotis Mertikopoulos () · Nicholas Bambos () · Stephen Boyd (Stanford University) · Peter W Glynn (Stanford University)

。