2020/10/2 09:00

機械学習のトップカンファレンスであるNeurIPS2020において、理研AIPセンターから21本の論文が採択されました。
[NeurIPS 2020] https://neurips.cc/Conferences/2020/AcceptedPapersInitial

Orals

  • Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
    Takeshi Teshima* (The University of Tokyo / RIKEN AIP)
    Isao Ishikawa* (Ehime University / RIKEN AIP)
    Koichi Tojo (RIKEN AIP)
    Kenta Oono (The University of Tokyo / Preferred Networks)
    Masahiro Ikeda (RIKEN AIP)
    Masashi Sugiyama (RIKEN AIP/ The University of Tokyo)
  • Continual Deep Learning by Functional Regularisation of Memorable Past
    P. Pan*+ (UT Sydney)
    S. Swaroop* (U Cambridge)
    A. Immer+ (EPFL)
    R. Eschenhagen+ (Max-Planck Tubingen)
    R.E. Turner (U Cambridge)
    M.E. Khan (RIKEN AIP)

(Acceptance rate 1.1%=105/9454)

Spotlights

  • Parts-dependent Label Noise: Towards Instance-dependent Label Noise
    Xiaobo Xia (The University of Sydney / Xidian University)
    Tongliang Liu ( The University of Sydney / RIKEN AIP)
    Bo Han (HKBU / RIKEN AIP)
    Nannan Wang (Xidian University)
    Mingming Gong (University of Melbourne)
    Haifeng Liu (Brain-Inspired Technology Co., Ltd.)
    Gang Niu (RIKEN AIP)
    Dacheng Tao (The University of Sydney)
    Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  • Rethinking Importance Weighting for Deep Learning under Distribution Shift
    Tongtong Fang (KTH Royal Institute of Technology) *+
    Nan Lu (The University of Tokyo / RIKEN AIP)*
    Gang Niu (RIKEN AIP)
    Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  • Neural Methods for Point-wise Dependency Estimation
    Yao-Hung Hubert Tsai (Carnegie Mellon University)
    Han Zhao (D.E. Shaw & Co)
    Makoto Yamada (Kyoto University / RIKEN AIP)
    Louis-Philippe Morency (Carnegie Mellon University)
    Ruslan Salakhutdinov (Carnegie Mellon University)
  • Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics
    Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  • Delay and Cooperation in Nonstochastic Linear Bandits
    Shinji Ito (NEC Corporation)
    Daisuke Hatano (RIKEN AIP)
    Hanna Sumita (Tokyo Institute of Technology)
    Kei Takemura (NEC Corporation)
    Takuro Fukunaga (Chuo University / JST PRESTO / RIKEN AIP)
    Naonori Kakimura (Keio University)
    Ken-ichi Kawarabayashi (National Institute of Informatics)
  • Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming
    Duy N.L.V. (Nagoya Insititute of Technology)
    Toda H. (Nagoya Insititute of Technology)
    Sugiyama R. (Nagoya Insititute of Technology)
    Takeuchi I. (Nagoya Insititute of Technology / RIKEN AIP)
  • Demixed shared component analysis of neural population data from multiple brain areas
    Yu Takagi (University of Oxford)
    Steven Kennerley (Institute of Neurology Sobell Dept., University College of London)
    Jun-ichiro Hirayama (AIST / RIKEN AIP)
    Laurence Hunt (University of Oxford)

(Acceptance rate 3.0%=280/9454)

Posters

  • Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
    Yu Yao (The University of Sydney)
    Tongliang Liu (The University of Sydney / RIKEN AIP)
    Bo Han (HKBU / RIKEN AIP)
    Mingming Gong (University of Melbourne)
    Jiankang Deng (Imperial College London)
    Gang Niu (RIKEN AIP)
    Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  • Provably Consistent Partial-Label Learning
    Lei Feng (Nanyang Technological University) +
    Jiaqi Lv (Southeast University) +
    Bo Han (HKBU / RIKEN AIP)
    Miao Xu (RIKEN AIP / University of Queensland)
    Gang Niu (RIKEN AIP)
    Xin Geng (Southeast University)
    Bo An (Nanyang Technological University)
    Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  • Learning from Aggregate Observations
    Yivan Zhang (The University of Tokyo / RIKEN AIP)
    Nontawat Charoenphakdee (The University of Tokyo / RIKEN AIP)
    Zhenguo Wu (The University of Tokyo)
    Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  • Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
    Taira Tsuchiya (The University of Tokyo / RIKEN AIP)
    Junya Honda (The University of Tokyo / RIKEN AIP)
    Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  • Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering
    Chen, L. (Nanjing University)
    Yao Y. (Nanjing University)
    Tong H. (UIUC)
    Xu M (the University of Queensland / RIKEN AIP)
    Xu F. (Nanjing University)
  • Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
    Xiang Li (NJUST)
    Wenhai Wang (Nanjing University)
    Lijun Wu (Microsoft Research)
    Shuo Chen (RIKEN AIP / NJUST)
    Xiaolin Hu (Tsinghua University)
    Jun Li (NJUST)
    Jinhui Tang (NJUST)
    Jian Yang (NJUST)
  • Fast Unbalanced Optimal Transport on Tree
    Ryoma Sato (Kyoto University / RIKEN AIP)
    Makoto Yamada (Kyoto University / RIKEN AIP)
    Hisashi Kashima (Kyoto University / RIKEN AIP)
  • Neural Star Domain as Primitive Representation
    Yuki Kawana (The University of Tokyo)
    Tatsuya Harada (The University of Tokyo / RIKEN AIP)
  • Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
    Kenta Oono (The University of Tokyo / Preferred Networks, Inc.)
    Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  • Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions
    Hayata Yamasaki (IQOQI Vienna)
    Sathyawageeswar Subramanian (University of Cambridge)
    Sho Sonoda (RIKEN AIP)
    Masato Koashi (Photon Science Center, The University of Tokyo / Department of Applied Physics, The University of Tokyo)
  • Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate
    Akifumi Okuno (The Institute of Statistical Mathematics / RIKEN AIP)
    Hidetoshi Shimodaira (Kyoto University / RIKEN AIP)
  • Robust Persistence Diagrams using Reproducing Kernels
    Siddharth Vishwanath (The Pennsylvania State University)
    Kenji Fukumizu (Institute of Statistical Mathematics / Preferred Networks / RIKEN AIP)
    Satoshi Kuriki (Institute of Statistical Mathematics)
    Bharath Sriperumbudur (Penn State University)

(Acceptance rate 20.1%=1900/9454)

*共同筆頭著者
+過去に実習生としてAIPセンターに所属

更新:2020/10/22, 2020/10/02 14:30

関連研究室

last updated on 2024/9/18 09:24研究室
last updated on 2023/6/26 10:54研究室
last updated on 2024/9/18 09:21研究室
last updated on 2024/9/18 09:15研究室
last updated on 2023/4/1 00:27研究室
last updated on 2024/8/22 15:22研究室
last updated on 2022/4/1 00:03研究室
last updated on 2024/6/13 10:32研究室
last updated on 2024/9/18 09:11研究室
last updated on 2022/4/1 00:07研究室