革新知能統合研究センター

機械学習のトップカンファレンスであるNeurIPS2019において、理研AIPセンターから21本の論文と1点のデモンストレーションが採択されました。

[NeurIPS 2019] https://neurips.cc/Conferences/2019/AcceptedPapersInitial

• Computing Full Conformal Prediction Set with Approximate Homotopy
  Ndiaye Eugene (RIKEN AIP)
  Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN AIP)
• Fast Sparse Group Lasso
  Yasutoshi Ida (NTT)
  Yasuhiro Fujiwara (NTT Software Innovation Center)
  Hisashi Kashima (Kyoto University / RIKEN AIP)
• Fully Neural Network based Model for General Temporal Point Processes
  Takahiro Omi (The University of Tokyo, RIKEN AIP)
  Naonori Ueda (RIKEN AIP)
  Kazuyuki Aihara (The University of Tokyo)
• Kernel Stein Tests for Multiple Model Comparison
  Jen Ning Lim (Max Planck Institute for Intelligent Systems)
  Makoto Yamada (Kyoto University / RIKEN AIP)
  Bernhard Scholkopf (MPI for Intelligent Systems)
  Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems)
• On the Calibration of Multiclass Classification with Rejection
  Chenri Ni (The University of Tokyo)
  Nontawat Charoenphakdee (The University of Tokyo / RIKEN AIP)
  Junya Honda (The University of Tokyo / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Learning Robust Options by Conditional Value at Risk Optimization
  Takuya Hiraoka (NEC / AIST / RIKEN-AIP) 
  Takahisa Imagawa (National Institute of Advanced Industrial Science and Technology)
  Tatsuya Mori (NEC)
  Takashi Onishi (NEC)
  Yoshimasa Tsuruoka (The University of Tokyo)
• Approximate Inference Turns Deep Networks into Gaussian Processes
  Mohammad Emtiyaz Khan (RIKEN AIP)
  Alexander Immer (EPFL)
  Ehsan Abedi (EPFL)
  Maciej Jan Korzepa (Technical University of Denmark)
• Uncoupled Regression from Pairwise Comparison Data
  Liyuan Xu (The University of Tokyo / RIKEN AIP)
  Junya Honda (University of Tokyo / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Approximation Ratios of Graph Neural Networks for Combinatorial Problems
  Ryoma Sato (Kyoto University / RIKEN AIP)
  Makoto Yamada (Kyoto University / RIKEN AIP)
  Hisashi Kashima (Kyoto University / RIKEN AIP)
• Data Cleansing for Models Trained with SGD
  Satoshi Hara (Osaka University)
  Atsushi Nitanda (The University of Tokyo / RIKEN AIP)
  Takanori Maehara (RIKEN AIP)
• Practical Deep Learning with Bayesian Principles
  Kazuki Osawa (Tokyo Institute of Technology)
  Siddharth Swaroop (University of Cambridge)
  Mohammad Emtiyaz Khan (RIKEN AIP)
  Anirudh Jain (Indian Institute of Technology (ISM), Dhanbad)
  Runa Eschenhagen (University of Osnabrueck)
  Richard E Turner (University of Cambridge)
  Rio Yokota (AIST Tokyo Tech RWBC-OIL)
• Discriminator optimal transport
  Akinori Tanaka (RIKEN AIP / iTHEMS / Keio University)
• Are Anchor Points Really Indispensable in Label-Noise Learning?
  Xiaobo Xia (Xidian University)
  Tongliang Liu (The University of Sydney)
  Nannan Wang (Xidian University)
  Bo Han (RIKEN AIP / HKBU)
  Chen Gong (Nanjing University of Science and Technology)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Fisher Efficient Inference of Intractable Models
  Song Liu (University of Bristol)
  Takafumi Kanamori (Tokyo Institute of Technology / RIKEN AIP)
  Wittawat Jitkrittum (Max Planck Institute for Intelligent Systems)
  Yu Chen (University of Bristol)
• Learning Macroscopic Brain Connectomes via Group-Sparse Factorization
  Farzane Aminmansour (University of Alberta)
  Andrew Patterson (University of Alberta)
  Lei Le (Indiana University Bloomington)
  Yisu Peng (Northeastern University)
  Daniel Mitchell (University of Alberta)
  Franco Pestilli (Indiana University)
  Cesar Caiafa (CONICET/RIKEN AIP)
  Russell Greiner (University of Alberta)
  Martha White (University of Alberta)
• Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback
  Shinji Ito (NEC Corporation / University of Tokyo)
  Daisuke Hatano (RIKEN AIP)
  Sumita Hanna (Tokyo Metropolitan University)
  Kei Takemura (NEC Corporation)
  Takuro Fukunaga (Chuo University / JST PRESTO / RIKEN AIP)
  Naonori Kakimura (Keio University)
  Ken-Ichi Kawarabayashi (National Institute of Informatics)
• Theoretical evidence for adversarial robustness through randomization
  Rafael Pinot (Dauphine University – CEA LIST)
  Laurent Meunier (Dauphine University – FAIR Paris)
  Alexandre Araujo (Université Paris-Dauphine – Wavestone)
  Hisashi Kashima (Kyoto University / RIKEN AIP)
  Florian Yger (Université Paris-Dauphine)
  Cedric Gouy-Pailler (CEA)
  Jamal Atif (Université Paris-Dauphine)
• Improved Regret Bounds for Bandit Combinatorial Optimization
  Shinji Ito (NEC Corporation / University of Tokyo)
  Daisuke Hatano (RIKEN AIP)
  Sumita Hanna (Tokyo Metropolitan University)
  Kei Takemura (NEC Corporation)
  Takuro Fukunaga (Chuo University / JST PRESTO / RIKEN AIP)
  Naonori Kakimura (Keio University)
  Ken-Ichi Kawarabayashi (National Institute of Informatics)
• Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling
  Ming Hou (RIKEN AIP)
  Jiajia Tang (Hangzhou Dianzi University / RIKEN AIP)
  Jianhai Zhang (Hangzhou Dianzi University)
  Wanzeng Kong (Hangzhou Dianzi University)
  Qibin Zhao (RIKEN AIP)
• Tree-Sliced Variants of Wasserstein Distances
  Tam Le (RIKEN AIP)
  Makoto Yamada (Kyoto University / RIKEN AIP)
  Kenji Fukumizu (Institute of Statistical Mathematics / Preferred Networks / RIKEN AIP)
  Marco Cuturi (Google and CREST / ENSAE)
• Semi-flat minima and saddle points by embedding neural networks to overparameterization
  Kenji Fukumizu (Institute of Statistical Mathematics / Preferred Networks / RIKEN AIP)
  Shoichiro Yamaguchi (Preferred Networks)
  Yoh-ichi Mototake (Institute of Statistical Mathematics)
  Mirai Tanaka (The Institute of Statistical Mathematics / RIKEN AIP)

Tutorial

• Deep Learning with Bayesian Principles
  Mohammad Emtiyaz Khan (RIKEN AIP)

Demonstration

• Melody Slot Machine
  Masatoshi Hamanaka (RIKEN AIP)

更新：2019/11/21

関連研究室