Center for Advanced Intelligence Project

23 papers were accepted at NeurIPS 2022, which is known as a top conference on machine learning.
For more details, please refer to the link below:

[NeurIPS 2022]

There were 10,411 full paper submissions to NeurIPS this year, of which the program committee accepted 25.6% for presentation at the conference.

• Adapting to Online Label Shift with Provable Guarantees
  Yong Bai (Nanjing University)
  Yu-Jie Zhang (The University of Tokyo)
  Peng Zhao (Nanjing University)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Zhi-Hua Zhou (Nanjing University)
• Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
  Jianan Zhou (Nanyang Technological University)
  Jianing Zhu (Hong Kong Baptist University)
  Jingfeng Zhang (RIKEN AIP)
  Tongliang Liu (University of Sydney / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning
  Kang-Jun Liu (GSIS, Tohoku University)
  Masanori Suganuma (GSIS, Tohoku University/RIKEN AIP)
  Takayuki Okatani (GSIS, Tohoku University/RIKEN AIP)
• Can Adversarial Training Be Manipulated By Non-Robust Features?
  Lue Tao (Nanjing University of Aeronautics and Astronautics)
  Lei Feng (Chongqing University / RIKEN AIP)
  Hongxin Wei (Nanyang Technological University)
  Jinfeng Yi (JD AI Research)
  Shengjun Huang (Nanjing University of Aeronautics and Astronautics)
  Songcan Chen (Nanjing University of Aeronautics and Astronautics)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
  Wuyang Chen (University of Texas Austin)
  Wei Huang (RIKEN AIP / University of Technology Sydney)
  Xinyu Gong (University of Texas, Austin)
  Boris Hanin (Princeton University)
  Zhangyang Wang (University of Texas at Austin)
• Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning
  Tomoya Murata (The University of Tokyo / NTT DATA Mathematical Systems Inc.)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
  Yuzhou Cao (Nanyang Technological University / Ant Group)
  Lei Feng (Chongqing University / RIKEN AIP)
  Tianchi Cai (Ant Group)
  Lihong Gu (Ant Group)
  Jinjie Gu (Ant Group)
  Bo An (Nanyang Technological University)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
  Jimmy Ba (University of Toronto / Vector Institute)
  Murat A. Erdogdu (University of Toronto / Vector Institute)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Zhichao Wang (Zhichao Wang)
  Denny Wu (University of Toronto / Vector Institute)
  Greg Yang (Microsoft Research)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization
  Yuri Kinoshita (The University of Tokyo)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Interpreting Operation Selection in Differentiable Architecture
  Search: A Perspective from Influence-Directed Explanations
  Miao Zhang (Monash University)
  Wei Huang (RIKEN AIP / University of Technology Sydney)
  Bin Yang (Aalborg University)
• Learning Contrastive Embedding in Low-Dimensional Space
  Shuo Chen (RIKEN AIP)
  Chen Gong (Nanjing University of Science and Technology)
  Jun Li (Nanjing University of Science and Technology)
  Jian Yang (Nanjing University of Science and Technology)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification
  Takumi Tanabe (University of Tsukuba / RIKEN AIP)
  Rei Sato (University of Tsukuba / RIKEN AIP)
  Kazuto Fukuchi (University of Tsukuba / RIKEN AIP)
  Jun Sakuma (University of Tsukuba / RIKEN AIP)
  Youhei Akimoto (University of Tsukuba / RIKEN AIP)
• Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
  Junpei Komiyama (New York University)
  Taira Tsuchiya (Kyoto University / RIKEN AIP)
  Junya Honda (Kyoto University / RIKEN AIP)
• Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
  Shinji Ito (NEC Corporation)
  Taira Tsuchiya (Kyoto University / RIKEN AIP)
  Junya Honda (Kyoto University / RIKEN AIP)
• Non-rigid Point Cloud Registration with Neural Deformation Pyramid
  Yang Li (The University of Tokyo)
  Tatsuya Harada (The University of Tokyo / RIKEN AIP)
• One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement
  Ning Xu (Southeast University)
  Congyu Qiao (Southeast University)
  Jiaqi Lv (RIKEN AIP)
  Xin Geng (Southeast University)
  Minling Zhang (Southeast University).
• Quantifying Statistical Significance of Neural Network-based Image Segmentation by Selective Inference
  Vo Nguyen Le Duy (Nagoya Institute of Technology / RIKEN)
  Shogo Iwazaki (Nagoya Institute of Technology)
  Ichiro Takeuchi (Nagoya University / RIKEN)
• Single Loop Gaussian Homotopy Method for Non-convex Optimization
  Hidenori Iwakiri (The University of Tokyo / RIKEN AIP)
  Yuhang Wang (The University of Tokyo)
  Shinji Ito (NEC Corporation / RIKEN AIP)*
  Akiko Takeda (The University of Tokyo / RIKEN AIP)
• SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
  Haobo Wang (Zhejiang University)
  Mingxuan Xia (Zhejiang University)
  Yixuan Li (University of Wisconsin–Madison)
  Yuren Mao (Zhejiang University)
  Lei Feng (Chongqing University / RIKEN AIP)
  Gang Chen (Zhejiang University)
  Junbo Zhao (Zhejiang University)
• SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG
  Reinmar J. Kobler (RIKEN AIP/ATR)
  Jun-ichiro Hirayama (RIKEN AIP)
  Qibin Zhao (RIKEN AIP)
  Motoaki Kawanabe (RIKEN AIP/ATR)
• Synergy-of-Experts: Collaborate to Improve Adversarial Robustness
  Sen Cui (Tsinghua University)
  Jingfeng Zhang (RIKEN AIP)
  Jian Liang (Alibaba)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Changshui Zhang (Tsinghua University)
• Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime
  Naoki Nishikawa (The University of Tokyo)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Atsushi Nitanda (Kyushu Institute of Technology / RIKEN AIP)
  Denny Wu (University of Toronto / Vector Institute)
• Universality of group convolutional neural networks based on ridgelet analysis on groups
  Sho Sonoda (RIKEN AIP / JST PRESTO)
  Isao Ishikawa (Ehime University)
  Masahiro Ikeda (RIKEN AIP)

*Visiting Scientist of the RIKEN AIP-NEC Collaboration Center until the end of March 2022.

Related Laboratories