Følg
Tomoya Sakai
Tomoya Sakai
IBM Research - Tokyo
Verifisert e-postadresse på ibm.com - Startside
Tittel
Sitert av
Sitert av
År
Do we need zero training loss after achieving zero training error?
T Ishida, I Yamane, T Sakai, G Niu, M Sugiyama
Proceedings of the Thirty-seventh International Conference on Machine …, 2020
1642020
Theoretical comparisons of positive-unlabeled learning against positive-negative learning
G Niu, MC du Plessis, T Sakai, Y Ma, M Sugiyama
Advances in Neural Information Processing Systems 29, 1199-1207, 2016
1512016
Semi-supervised classification based on classification from positive and unlabeled data
T Sakai, MC du Plessis, G Niu, M Sugiyama
Proceedings of the 34th International Conference on Machine Learning, 2998-3006, 2017
1382017
Semi-supervised AUC optimization based on positive-unlabeled learning
T Sakai, G Niu, M Sugiyama
Machine Learning 107, 767-794, 2018
692018
Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach
M Sugiyama, H Bao, T Ishida, N Lu, T Sakai, G Niu
MIT Press, 2022
362022
Covariate shift adaptation on learning from positive and unlabeled data
T Sakai, N Shimizu
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 4838-4845, 2019
232019
Convex formulation of multiple instance learning from positive and unlabeled bags
H Bao, T Sakai, I Sato, M Sugiyama
Neural Networks 105, 132-141, 2018
222018
Computationally efficient estimation of squared-loss mutual information with multiplicative kernel models
T Sakai, M Sugiyama
IEICE TRANSACTIONS on Information and Systems 97 (4), 968-971, 2014
162014
Regret minimization for causal inference on large treatment space
A Tanimoto, T Sakai, T Takenouchi, H Kashima
International Conference on Artificial Intelligence and Statistics, 946-954, 2021
142021
Least-squares log-density gradient clustering for Riemannian manifolds
M Ashizawa, H Sasaki, T Sakai, M Sugiyama
Artificial Intelligence and Statistics, 537-546, 2017
92017
Registration of infrared transmission images using squared-loss mutual information
T Sakai, M Sugiyama, K Kitagawa, K Suzuki
Precision Engineering 39, 187-193, 2015
62015
A Generalized Backward Compatibility Metric
T Sakai
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and …, 2022
42022
Robust modal regression with direct gradient approximation of modal regression risk
H Sasaki, T Sakai, T Kanamori
Conference on Uncertainty in Artificial Intelligence, 380-389, 2020
42020
Causal combinatorial factorization machines for set-wise recommendation
A Tanimoto, T Sakai, T Takenouchi, H Kashima
Pacific-Asia Conference on Knowledge Discovery and Data Mining, 498-509, 2021
32021
MLOps を促進する予測ミス要因の自動特定法
佐久間啓太， 坂井智哉， 亀田義男
人工知能学会全国大会論文集 第 35 回 (2021), 2G3GS2e04-2G3GS2e04, 2021
22021
Information-theoretic representation learning for positive-unlabeled classification
T Sakai, G Niu, M Sugiyama
Neural Computation 33 (1), 244-268, 2020
22020
Binary matrix completion using unobserved entries
M Hayashi, T Sakai, M Sugiyama
arXiv preprint arXiv:1803.04663, 2018
22018
Risk minimization framework for multiple instance learning from positive and unlabeled bags
H Bao, T Sakai, I Sato, M Sugiyama
arxiv preprint arxiv 1704, 2017
22017
A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
T Sakai, H Qiu, T Katsuki, D Kimura, T Osogami, T Inoue
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
12024
Distributionally robust model training
V Barsopia, Y Kameda, T Sakai
US Patent App. 17/392,261, 2022
12022
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20