1.4k citations
- Kyoto UniversityJP15 papers
- The University of TokyoJP14 papers
- Tokyo Institute of TechnologyJP7 papers
- University of TsukubaJP6 papers
- National Institute of Advanced Industrial Science and TechnologyJP5 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)DE3 papers
- Institut polytechnique de GrenobleFR3 papers
- Japan Atomic Energy AgencyJP3 papers
- Kyoto College of Graduate Studies for InformaticsJP3 papers
- Kyushu UniversityJP3 papers
- Nara Institute of Science and TechnologyJP3 papers
9 papers · 1 filter
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
Xiong Peng, Feng Liu, Jingfen Zhang +4
Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training dat…
Best-of-Both-Worlds Algorithms for Partial Monitoring
Taira Tsuchiya, Shinji Ito, Junya Honda
This study considers the partial monitoring problem with -actions and -outcomes and provides the first best-of-both-worlds algorithms, whose regrets are favorably bounded bot…
Efficient Tensor Robust PCA under Hybrid Model of Tucker and Tensor Train
Yuning Qiu, Guoxu Zhou, Zhenhao Huang +2
Tensor robust principal component analysis (TRPCA) is a fundamental model in machine learning and computer vision. Recently, tensor train (TT) decomposition has been verified effec…
Application of Adversarial Examples to Physical ECG Signals
Taiga Ono, Takeshi Sugawara, Jun Sakuma +1
This work aims to assess the reality and feasibility of the adversarial attack against cardiac diagnosis system powered by machine learning algorithms. To this end, we introduce ad…
LocalDrop: A Hybrid Regularization for Deep Neural Networks
Ziqing Lu, Chang Xu, Bo Du +3
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas. We propose a new approach for the regularization of neural networks…
Binary classification with ambiguous training data
Naoya Otani, Yosuke Otsubo, Tetsuya Koike +1
In supervised learning, we often face with ambiguous (A) samples that are difficult to label even by domain experts. In this paper, we consider a binary classification problem in t…