May 16, 2019 13:52

14 papers have been accepted at ICML 2019, a top conference on machine learning. For more details, please refer to the link below.


  • Classification from Positive, Unlabeled and Biased Negative Data
    Yu-Guan Hsieh (Ecole normale superieure) *
    Gang Niu (RIKEN)
    Masashi Sugiyama (RIKEN/The University of Tokyo)
  • Imitation Learning from Imperfect Demonstration
    Yueh-Hua Wu (National Taiwan University) *
    Nontawat Charoenphakdee (The University of Tokyo / RIKEN)
    Han Bao (The University of Tokyo / RIKEN)
    Voot Tangkaratt (RIKEN)
    Masashi Sugiyama (RIKEN/The University of Tokyo)
  • How does Disagreement Help Generalization against Label Corruption?
    Xingrui Yu (University of Technology Sydney)
    Bo Han (RIKEN)
    Jiangchao Yao (University of Technology Sydney)
    Gang Niu (RIKEN)
    Ivor Tsang (University of Technology Sydney)
    Masashi Sugiyama (RIKEN/The University of Tokyo)
  • On Symmetric Losses for Learning from Corrupted Labels
    Nontawat Charoenphakdee (The University of Tokyo/RIKEN)
    Jongyeong Lee (The University of Tokyo/RIKEN)
    Masashi Sugiyama (RIKEN/The University of Tokyo)
  • Complementary-Label Learning for Arbitrary Losses and Models
    Takashi Ishida (University of Tokyo/RIKEN)
    Gang Niu (RIKEN)
    Aditya Menon (Australian National University)
    Masashi Sugiyama (RIKEN/The University of Tokyo)
  • Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
    Quanming Yao (4Paradigm. Inc.)
    James T. Kwok (Hong Kong University of Science and Technology)
    Bo Han (RIKEN)
  • Safe Grid Search with Optimal Complexity
    Eugene Ndiaye (RIKEN AIP)
    Tam Le (RIKEN AIP)
    Olivier Fercoq (Télécom ParisTech, Université Paris-Saclay)
    Joseph Salmon (Université de Montpellier)
    Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN)
  • Scalable Training of Inference Networks for Gaussian-Process Models
    Jiaxin Shi (Tsinghua University) *
    Mohammad Emtiyaz Khan (RIKEN)
    Jun Zhu (Tsinghua University)
  • Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
    Wu Lin (UBC)
    Mohammad Emtiyaz Khan (RIKEN)
    Mark Schmidt (University of British Columbia)
  • Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks
    Kenta Oono (University of Tokyo/Preferred Networks)
    Taiji Suzuki (The University of Tokyo/RIKEN)
  • Fairwashing: the risk of rationalization
    Ulrich Aivodji (Universite du Quebec a Montreal [UQAM])
    Hiromi Arai (RIKEN Center for Advanced Intelligence Project [AIP]/JST PRESTO)
    Olivier Fortineau (ENSTA-Paristech)
    Sebastien Gambs (Universite du Quebec a Montreal [UQAM])
    Satoshi Hara (Osaka University)
    Alain Tapp (Universite de Montreal)
  • Kernel Normalized Cut: a Theoretical Revisit
    Yoshikazu Terada (Osaka University/RIKEN)
    Michio Yamamoto (Okayama University/RIKEN)
  • Simple Stochastic Gradient Methods for Non-Smooth Non-ConvexRegularized Optimization
    Michael Metel (RIKEN Center for Advanced Intelligence Project)
    Akiko Takeda (The University of Tokyo/RIKEN Center for Advanced Intelligence Project)
  • Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search
    Youhei Akimoto (University of Tsukuba / RIKEN AIP)
    Shinichi Shirakawa (Yokohama National University)
    Nozomu Yoshinari (Yokohama National University)
    Kento Uchida (Yokohama National University)
    Shota Saito (Yokohama National University)
    Kouhei Nishida (Shinshu University)

*They are past interns of RIKEN AIP.

Updated: May 22, 2019

Related Laboratories

last updated on September 25, 2023 10:07Laboratory
last updated on June 26, 2023 10:54Laboratory
last updated on September 25, 2023 10:04Laboratory
last updated on June 26, 2023 11:35Laboratory
last updated on September 25, 2023 10:01Laboratory
last updated on June 26, 2023 15:23Laboratory
last updated on April 1, 2022 00:03Laboratory
last updated on June 27, 2023 08:45Laboratory
last updated on June 28, 2023 14:11Laboratory