Kazuki Osawa
Title
Cited by
Cited by
Year
Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks
K Osawa, Y Tsuji, Y Ueno, A Naruse, R Yokota, S Matsuoka
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp …, 2019
56*2019
Practical deep learning with bayesian principles
K Osawa, S Swaroop, A Jain, R Eschenhagen, RE Turner, R Yokota, ...
arXiv preprint arXiv:1906.02506, 2019
522019
Accelerating matrix multiplication in deep learning by using low-rank approximation
K Osawa, A Sekiya, H Naganuma, R Yokota
2017 International Conference on High Performance Computing & Simulation …, 2017
92017
Performance optimizations and analysis of distributed deep learning with approximated second-order optimization method
Y Tsuji, K Osawa, Y Ueno, A Naruse, R Yokota, S Matsuoka
Proceedings of the 48th International Conference on Parallel Processing …, 2019
32019
Evaluating the compression efficiency of the filters in convolutional neural networks
K Osawa, R Yokota
International Conference on Artificial Neural Networks, 459-466, 2017
32017
Scalable and practical natural gradient for large-scale deep learning
K Osawa, Y Tsuji, Y Ueno, A Naruse, CS Foo, R Yokota
arXiv preprint arXiv:2002.06015, 2020
22020
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks
R Karakida, K Osawa
arXiv preprint arXiv:2010.00879, 2020
2020
Rich Information is Affordable: A Systematic Performance Analysis of Second-order Optimization Using K-FAC
Y Ueno, K Osawa, Y Tsuji, A Naruse, R Yokota
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–8