機械学習の主要なカンファレンスであるICLR 2023において、AIPセンターから7本の論文が採択されました。
[Accepted Papers] https://openreview.net/group?id=ICLR.cc/2023/Conference
全投稿数は4966編で，３種類の採択がありました．
採択率は下記の通りです。
– Notable-top-5%: Acceptance rate 1.6%
Traditionally called Accept (oral)
– Notable-top-25%: Acceptance rate 8.0%
Traditionally called Accept (spotlight)
– Poster: Acceptance rate 31.8%
[Notable-top-5%]
- Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Takashi Ishida (The University of Tokyo)
Ikko Yamane (Ecole Nationale de la Statistique et de l’Analyse de l’information)
Nontawat Charoenphakdee (The University of Tokyo)
Gang Niu (RIKEN AIP)
Masashi Sugiyama (RIKEN AIP/ The University of Tokyo)
https://openreview.net/forum?id=FZdJQgy05rz
- SAM as an Optimal Relaxation of Bayes
Thomas Möllenhoff (RIKEN AIP）
Mohammad Emtiyaz Khan (RIKEN AIP）
https://openreview.net/forum?id=k4fevFqSQcX
[Notable-top-25%]
- Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
Xin-Qiang Cai (The University of Tokyo)
Yao-Xiang Ding (Zhejiang University)
Zixuan Chen (Nanjing University)
Yuan Jiang (Nanjing University)
Masashi Sugiyama (RIKEN/The University of Tokyo)
Zhi-Hua Zhou (Nanjing University)
https://openreview.net/forum?id=3ULaIHxn9u7
[Poster]
- 3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation
Zhennan Wu (The University of Tokyo / RIKEN AIP)
Yang Li (The University of Tokyo)
Yifei Huang (The University of Tokyo)
Lin Gu (RIKEN AIP)
Tatsuya Harada(The University of Tokyo, RIKEN AIP)
Hiroyuki Sato (The University of Tokyo)
https://openreview.net/forum?id=4dZeBJ83oxk
- Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
Shunta Akiyama (The University of Tokyo),
Taiji Suzuki (The University of Tokyo / RIKEN AIP)
https://openreview.net/forum?id=6doXHqwMayf
- Uniform-in-time propagation of chaos for the mean field gradient Langevin dynamics
Taiji Suzuki (The University of Tokyo / RIKEN AIP )
Atsushi Nitanda (Kyushu Institute of Technology / RIKEN AIP / JST PRESTO)
Denny Wu (University of Toronto / Vector Institute) +
https://openreview.net/forum?id=_JScUk9TBUn
- Valid P-Value for Deep Learning-driven Salient Region
Daiki Miwa (Nagoya Institute of Technology)
Vo Nguyen Le Duy (RIKEN AIP)
Ichiro Takeuchi (Nagoya University / RIKEN AIP)
https://openreview.net/forum?id=qihMOPw4Sf_
+ 過去に実習生としてAIPセンターに所属
