Masashi Sugiyama

发表

LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning pdf

Kei Mukaiyama, Issei Sato, Masashi Sugiyama, 2020, ArXiv.

Geometry-aware Instance-reweighted Adversarial Training pdf

Gang Niu, Masashi Sugiyama, Bo Han, 2020, ArXiv.

Active Learning in Policy Iteration

Masashi Sugiyama, 2015 .

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators pdf

Masashi Sugiyama, Takeshi Teshima, Kenta Oono, 2020, NeurIPS.

On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective pdf

Jayakorn Vongkulbhisal, Masashi Sugiyama, Nontawat Charoenphakdee, 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Iteratively-reweighted local model fitting method for adaptive and accurate single-shot surface profiling.

Hidemitsu Ogawa, Masashi Sugiyama, Kazuyoshi Suzuki, 2010, Applied optics.

Stochastic Multichannel Ranking with Brain Dynamics Preferences

Ivor W. Tsang, Chin-Teng Lin, Masashi Sugiyama, 2020, Neural Computation.

Issei Sato, Masashi Sugiyama, Liyuan Xu, 2020, ArXiv.

Combinatorial Pure Exploration with Full-bandit Feedback and Beyond: Solving Combinatorial Optimization under Uncertainty with Limited Observation pdf

Masashi Sugiyama, Yuko Kuroki, Junya Honda, 2020, ArXiv.

An analytic formulation for positive-unlabeled learning via weighted integral probability metric.

Masashi Sugiyama, Yongchan Kwon, Myunghee Cho Paik, 2019 .

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring pdf

Masashi Sugiyama, Junya Honda, Taira Tsuchiya, 2020, NeurIPS.

Policy-Prior Search

Masashi Sugiyama, 2015 .

Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics

Masashi Sugiyama, Masato Ishii, Masashi Sugiyama, 2021, ArXiv.

A computationally-efficient alternative to kernel logistic regression

Masashi Sugiyama, J. Simm, Masashi Sugiyama, 2010, 2010 IEEE International Workshop on Machine Learning for Signal Processing.

Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels

Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama, 2020, ICML.

Single-shot surface profiling by local model fitting.

Hidemitsu Ogawa, Masashi Sugiyama, Kazuyoshi Suzuki, 2006, Applied optics.

Accelerating the diffusion-based ensemble sampling by non-reversible dynamics

Masashi Sugiyama, Issei Sato, Futoshi Futami, 2020, ICML.

Variational Imitation Learning with Diverse-quality Demonstrations

Mohammad Emtiyaz Khan, Voot Tangkaratt, Masashi Sugiyama, 2020, ICML.

Maximum Mean Discrepancy is Aware of Adversarial Attacks pdf

Tongliang Liu, Masashi Sugiyama, Bo Han, 2020, ArXiv.

Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time pdf

Issei Sato, Masashi Sugiyama, Nontawat Charoenphakdee, 2020, ArXiv.

Interpolated local model fitting method for accurate and fast single-shot surface profiling.

Hidemitsu Ogawa, Tatsuya Yokota, Masashi Sugiyama, 2009, Applied optics.

Automatic parameter optimization of the local model fitting method for single-shot surface profiling.

Hidemitsu Ogawa, Masashi Sugiyama, Katsuichi Kitagawa, 2011, Applied optics.

Statistical outlier detection for diagnosis of cyber attacks in power state estimation

Song Liu, Masashi Sugiyama, Hideaki Ishii, 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting pdf

Masashi Sugiyama, Issei Sato, Dacheng Tao, 2020, ArXiv.

Stable Weight Decay Regularization pdf

Masashi Sugiyama, Issei Sato, Zeke Xie, 2020, ArXiv.

Pointwise Binary Classification with Pairwise Confidence Comparisons pdf

Gang Niu, Masashi Sugiyama, Bo Han, 2020, ArXiv.

A Survey of Label-noise Representation Learning: Past, Present and Future pdf

Ivor W. Tsang, James T. Kwok, Tongliang Liu, 2020, ArXiv.

Partially Zero-shot Domain Adaptation from Incomplete Target Data with Missing Classes

Masashi Sugiyama, Takashi Takenouchi, Masato Ishii, 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

Calibrated Surrogate Losses for Adversarially Robust Classification pdf

Masashi Sugiyama, Clayton Scott, Han Bao, 2020, COLT 2020.

S2GA: Robust Deep Learning with Noisy Labels without Early Stopping

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2020, ICML 2020.

A Symmetric Loss Perspective of Reliable Machine Learning pdf

Masashi Sugiyama, Nontawat Charoenphakdee, Jongyeong Lee, 2021, ArXiv.

$\gamma$-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator

Issei Sato, Masashi Sugiyama, Takeshi Teshima, 2020 .

Binary classification with ambiguous training data

Masashi Sugiyama, Yosuke Otsubo, Tetsuya Koike, 2020, Machine Learning.

Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent pdf

Masashi Sugiyama, Mehdi Abbana Bennani, Masashi Sugiyama, 2020, ArXiv.

Sample Reuse in Policy Iteration

Masashi Sugiyama, 2015 .

Multiwavelength-integrated local model fitting method for interferometric surface profiling.

Masashi Sugiyama, Katsuichi Kitagawa, Akihiro Yamashita, 2012, Applied optics.

A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima.

Masashi Sugiyama, Issei Sato, Zeke Xie, 2020 .

Using product-of-Student-t for labal propagation on multiple networks

Masashi Sugiyama, 杉山将, 2008 .

Learning from Aggregate Observations pdf

Masashi Sugiyama, Nontawat Charoenphakdee, Yivan Zhang, 2020, NeurIPS.

Online Dense Subgraph Discovery via Blurred-Graph Feedback pdf

Masashi Sugiyama, Atsushi Miyauchi, Yuko Kuroki, 2020, ICML.

A One-Step Approach to Covariate Shift Adaptation pdf

Tianyi Zhang, Masashi Sugiyama, Nan Lu, 2020, SN Computer Science.

Progressive Identification of True Labels for Partial-Label Learning pdf

Gang Niu, Masashi Sugiyama, Miao Xu, 2020, ICML.

Are Registration Uncertainty and Error Monotonically Associated?

William M. Wells, Masashi Sugiyama, Duo Wang, 2020, MICCAI.

Calibrated Surrogate Maximization of Dice

Atsuto Maki, Masashi Sugiyama, Han Bao, 2020, MICCAI.

SIGUA: Forgetting May Make Learning with Noisy Labels More Robust

Xingrui Yu, Ivor W. Tsang, Gang Niu, 2018, ICML.

Do Public Datasets Assure Unbiased Comparisons for Registration Evaluation? pdf

Nazim Haouchine, Zhe Xu, Masashi Sugiyama, 2020, ArXiv.

Robust Imitation Learning from Noisy Demonstrations pdf

Voot Tangkaratt, Masashi Sugiyama, Nontawat Charoenphakdee, 2020, ArXiv.

Improved algorithm for multiwavelength single-shot interferometric surface profiling: speeding up the multiwavelength-integrated local model fitting method by local information sharing.

Masashi Sugiyama, Katsuichi Kitagawa, Masafumi Otsuki, 2013, Applied optics.

Robust Policy Iteration

Masashi Sugiyama, 2015 .

Binary Classification from Positive Data with Skewed Confidence

Masashi Sugiyama, Hirotaka Kaji, Kazuhiko Shinoda, 2020, International Joint Conference on Artificial Intelligence.

Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum pdf

Masashi Sugiyama, Huishuai Zhang, Issei Sato, 2020, ICML.

Unsupervised key frame selection using information theory and colour histogram difference

Janya Sainui, Masashi Sugiyama, 2020, Int. J. Bus. Intell. Data Min..

Parts-dependent Label Noise: Towards Instance-dependent Label Noise pdf

Gang Niu, Nannan Wang, Tongliang Liu, 2020, ArXiv.

Registration of infrared transmission images using squared-loss mutual information

Tomoya Sakai, Masashi Sugiyama, Kazuyoshi Suzuki, 2015 .

Wildly Unsupervised Domain Adaptation and Its Powerful and Efficient Solution

Gang Niu, Feng Liu, Masashi Sugiyama, 2019 .

A Diffusion Theory For Minima Selection: Stochastic Gradient Descent Escapes Sharp Minima Exponentially Fast

Masashi Sugiyama, Issei Sato, Zeke Xie, 2020 .

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning pdf

Gang Niu, Yu Yao, Tongliang Liu, 2020, NeurIPS.

Provably Consistent Partial-Label Learning pdf

Gang Niu, Masashi Sugiyama, Bo Han, 2020, NeurIPS.

Do We Need Zero Training Loss After Achieving Zero Training Error?

Gang Niu, Tomoya Sakai, Masashi Sugiyama, 2020, ICML.

Classification with Rejection Based on Cost-sensitive Classification pdf

Masashi Sugiyama, Nontawat Charoenphakdee, Zhenghang Cui, 2020, ArXiv.

Rethinking Importance Weighting for Deep Learning under Distribution Shift pdf

Gang Niu, Masashi Sugiyama, Nan Lu, 2020, NeurIPS.

Provably End-to-end Label-Noise Learning without Anchor Points

Gang Niu, Masashi Sugiyama, Tongliang Liu, 2021, ICML.

Classification with Rejection Based on Cost-sensitive Classification pdf

Masashi Sugiyama, Nontawat Charoenphakdee, Zhenghang Cui, 2020, ICML.

Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting

Dacheng Tao, Masashi Sugiyama, Issei Sato, 2021, Neural Computation.

Maximum Mean Discrepancy Test is Aware of Adversarial Attacks

Masashi Sugiyama, Jingfeng Zhang, Tongliang Liu, 2020, ICML.

Instance Correction for Learning with Open-set Noisy Labels pdf

Mingming Gong, Masashi Sugiyama, Tongliang Liu, 2021, ArXiv.

Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization

Gang Niu, Masashi Sugiyama, Yivan Zhang, 2021, ICML.

Towards Adversarially Robust Deep Image Denoising pdf

Masashi Sugiyama, Jiashi Feng, Hanshu Yan, 2022, IJCAI.

Understanding the Interaction of Adversarial Training with Noisy Labels pdf

Hongxia Yang, Masashi Sugiyama, Jingfeng Zhang, 2021, ArXiv.

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification

Gang Niu, Masashi Sugiyama, Issei Sato, 2021, ICML.

A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima

Masashi Sugiyama, Issei Sato, Zeke Xie, 2020, ICLR.

LocalDrop: A Hybrid Regularization for Deep Neural Networks

Bo Du, Masashi Sugiyama, Lefei Zhang, 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Learning with Proper Partial Labels pdf

Masashi Sugiyama, Zhenguo Wu, 2021, ArXiv.

Geometry-aware Instance-reweighted Adversarial Training pdf

Gang Niu, Masashi Sugiyama, Jingfeng Zhang, 2021, ICLR.

Lower-bounded proper losses for weakly supervised classification pdf

Masashi Sugiyama, Takashi Takenouchi, Shuhei M. Yoshida, 2021, ICML.

Learning from Similarity-Confidence Data

Gang Niu, Masashi Sugiyama, Yuzhou Cao, 2021, ICML.

Approximating Instance-Dependent Noise via Instance-Confidence Embedding pdf

Masashi Sugiyama, Yivan Zhang, Masashi Sugiyama, 2021, ArXiv.

Fenchel-Young Losses with Skewed Entropies for Class-posterior Probability Estimation

Masashi Sugiyama, Han Bao, Masashi Sugiyama, 2021, AISTATS.

Probabilistic Margins for Instance Reweighting in Adversarial Training pdf

Chen Gong, Masashi Sugiyama, Tongliang Liu, 2021, ArXiv.

Active Refinement for Multi-Label Learning: A Pseudo-Label Approach pdf

Gang Niu, Miao Xu, Masashi Sugiyama, 2021, ArXiv.

Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation

Masashi Sugiyama, Takeshi Teshima, Masashi Sugiyama, 2021, UAI.

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection pdf

Gang Niu, Hanshu Yan, Jiashi Feng, 2021, ICML.

Discovering Diverse Solutions in Deep Reinforcement Learning pdf

Voot Tangkaratt, Masashi Sugiyama, Takayuki Osa, 2021, ArXiv.

Pointwise Binary Classification with Pairwise Confidence Comparisons

Gang Niu, Miao Xu, Masashi Sugiyama, 2021, ICML.

Multi-Class Classification from Single-Class Data with Confidences pdf

Gang Niu, Masashi Sugiyama, Senlin Shu, 2021, ArXiv.

Large-Margin Contrastive Learning with Distance Polarization Regularizer

Gang Niu, Chen Gong, Shuo Chen, 2021, ICML.

Rethinking Importance Weighting for Transfer Learning pdf

Masashi Sugiyama, Takeshi Teshima, Tongtong Fang, 2021, ArXiv.

On the Robustness of Average Losses for Partial-Label Learning pdf

Gang Niu, Miao Xu, Xin Geng, 2021, ArXiv.

Guided Interpolation for Adversarial Training pdf

Gang Niu, Chen Chen, Masashi Sugiyama, 2021, ArXiv.

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels pdf

Mingming Gong, Masashi Sugiyama, Tongliang Liu, 2021, ICLR.

Loss function based second-order Jensen inequality and its application to particle variational inference pdf

Naonori Ueda, Tomoharu Iwata, Masashi Sugiyama, 2021, NeurIPS.

Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences pdf

Florian Yger, Junya Honda, Masashi Sugiyama, 2021, ICML.

Seeing Differently, Acting Similarly: Imitation Learning with Heterogeneous Observations pdf

Zhi-Hua Zhou, Yuan Jiang, Masashi Sugiyama, 2021, ArXiv.

NoiLIn: Do Noisy Labels Always Hurt Adversarial Training? pdf

Masashi Sugiyama, Lizhen Cui, Jingfeng Zhang, 2021, ArXiv.

Demystifying Assumptions in Learning to Discover Novel Classes

Long Lan, Masashi Sugiyama, Tongliang Liu, 2021 .

Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization pdf

Zhanxing Zhu, Masashi Sugiyama, Zeke Xie, 2021, ICML.

Learning Diverse-Structured Networks for Adversarial Robustness pdf

Gang Niu, Junzhou Huang, Masashi Sugiyama, 2021, ICML.

Calibrated Surrogate Losses for Adversarially Robust Classification

Masashi Sugiyama, Clayton Scott, Han Bao, 2020, COLT.