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 International Conference on Machine Learning (ICML) 2022において、AIPセンターから11本の論文が採択されました。

[Website] https://icml.cc/Conferences/2022

[Accepted Papers] https://icml.cc/Conferences/2022/AcceptedPapersInitial

Long talk (3 papers)

• Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
  Zeke Xie ( The University of Tokyo/RIKEN AIP )
  Xinrui Wang ( The University of Tokyo/Tencent )
  Huishuai Zhang ( Microsoft )
  Issei Sato ( The University of Tokyo )
  Masashi Sugiyama ( RIKEN/The University of Tokyo )
• Re-evaluating Word Mover’s Distance
  Ryoma Sato (Kyoto University/RIKEN AIP)
  Makoto Yamada (Kyoto University/RIKEN AIP)
  Hisashi Kashima (Kyoto University/RIKEN AIP)
• To Smooth or Not? When Label Smoothing Meets Noisy Labels
  Jiaheng Wei ( UC Santa Cruz )
  Hangyu Liu ( Brown University )
  Tongliang Liu ( The University of Sydney )
  Gang Niu ( RIKEN AIP )
  Masashi Sugiyama ( RIKEN/The University of Tokyo )
  Yang Liu ( UC Santa Cruz )

Short talk (8 papers)

• Adversarial Attacks and Defenses for Non-Parametric Two-Sample Tests
  Xilie Xu ( National University of Singapore )
  Jingfeng Zhang ( RIKEN )
  Feng Liu ( University of Technology Sydney )
  Masashi Sugiyama ( RIKEN/The University of Tokyo )
  Mohan Kankanhalli ( National University of Singapore )
• Bayesian Optimization for Distributionally Robust Chance-constrained Problem
  Yu Inatsu (Nagoya Institute of Technology)
  Shion Takeno (Nagoya Institute of Technology)
  Masayuki Karasuyama (Nagoya Institute of Technology)
  Ichiro Takeuchi (Nagoya University / RIKEN AIP)
• Estimating Instance-dependent Label-noise Transition Matrix using a Deep Neural Network
  Shuo Yang ( University of Technology Sydney )
  Erkun Yang ( Xidian University )
  Bo Han ( HKBU / RIKEN )
  Yang Liu ( UC Santa Cruz )
  Min Xu ( University of Technology Sydney )
  Gang Niu ( RIKEN )
  Tongliang Liu ( The University of Sydney )
• Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
  Ruize Gao ( The Chinese University of Hong Kong )
  Jiongxiao Wang ( Fudan University )
  Kaiwen Zhou ( The Chinese University of Hong Kong )
  Feng Liu ( University of Technology Sydney )
  Binghui Xie ( The Chinese University of Hong Kong )
  Gang Niu ( RIKEN )
  Bo Han ( HKBU / RIKEN )
  James Cheng ( CUHK )
• Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis
  Sho Sonoda (RIKEN AIP)
  Isao Ishikawa (Ehime University)
  Masahiro Ikeda (RIKEN AIP)
• Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
  Matthias Weissenbacher (RIKEN AIP)
  Samarth Sinha (Meta AI Research)
  Animesh Garg (Univ. of Toronto / Vector Institute)
  Yoshinobu Kawahara (Kyushu Univ. / RIKEN AIP)
• On the Surrogate Gap between Contrastive and Supervised Losses
  Han Bao ( The University of Tokyo / RIKEN AIP, currently with Kyoto University )
  Yoshihiro Nagano ( The University of Tokyo / RIKEN AIP )
  Kento Nozawa ( The University of Tokyo / RIKEN AIP )
• Permutation Search of Tensor Network Structures via Local Sampling
  Chao Li (RIKEN-AIP)
  Junhua Zeng (Guangdong university of technology/RIKEN-AIP)
  Zerui Tao (Tokyo university of agriculture and technology/RIKEN-AIP)
  Qibin Zhao (RIKEN-AIP)

関連研究室