Follow
Kazuki Osawa
Kazuki Osawa
Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Practical deep learning with Bayesian principles
K Osawa, S Swaroop, MEE Khan, A Jain, R Eschenhagen, RE Turner, ...
Advances in neural information processing systems 32, 2019
2472019
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
143*2019
Scalable and practical natural gradient for large-scale deep learning
K Osawa, Y Tsuji, Y Ueno, A Naruse, CS Foo, R Yokota
IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (1), 404-415, 2020
362020
Understanding approximate fisher information for fast convergence of natural gradient descent in wide neural networks
R Karakida, K Osawa
Advances in neural information processing systems 33, 10891-10901, 2020
242020
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
212017
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
142020
Efficient quantized sparse matrix operations on tensor cores
S Li, K Osawa, T Hoefler
SC22: International Conference for High Performance Computing, Networking …, 2022
122022
Neural graph databases
M Besta, P Iff, F Scheidl, K Osawa, N Dryden, M Podstawski, T Chen, ...
Learning on Graphs Conference, 31: 1-31: 38, 2022
92022
Asdl: A unified interface for gradient preconditioning in pytorch
K Osawa, S Ishikawa, R Yokota, S Li, T Hoefler
arXiv preprint arXiv:2305.04684, 2023
82023
Pipefisher: Efficient training of large language models using pipelining and fisher information matrices
K Osawa, S Li, T Hoefler
Proceedings of Machine Learning and Systems 5, 2023
82023
Understanding gradient regularization in deep learning: Efficient finite-difference computation and implicit bias
R Karakida, T Takase, T Hayase, K Osawa
International Conference on Machine Learning, 15809-15827, 2023
72023
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
Workshop Proceedings of the 48th International Conference on Parallel …, 2019
72019
Second-order Optimization Method for Large Mini-batch: Training ResNet-50 on ImageNet in 35 Epochs.(2018)
K Osawa, Y Tsuji, Y Ueno, A Naruse, R Yokota, S Matsuoka
arXiv preprint arXiv:1811.12019, 2018
52018
Evaluating the compression efficiency of the filters in convolutional neural networks
K Osawa, R Yokota
Artificial Neural Networks and Machine Learning–ICANN 2017: 26th …, 2017
42017
Improving Continual Learning by Accurate Gradient Reconstructions of the Past
E Daxberger, S Swaroop, K Osawa, R Yokota, RE Turner, ...
Transactions on Machine Learning Research, 2023
12023
Efficient cluster mapping for conditions of weather based on combination of self-organizing map and hierarchical clustering
K Osawa, K Kamei, M Ishikawa
IEICE Technical Report; IEICE Tech. Rep. 119 (453), 213-218, 2020
12020
Accelerating Convolutional Neural Networks Using Low-Rank Tensor Decomposition
K Osawa, A Sekiya, H Naganuma, R Yokota
IEICE Technical Report; IEICE Tech. Rep. 117 (238), 1-6, 2017
2017
Examination about the salt solution filling packing method of sea urchin (Strongylocentrotus nudus) gonad
K Osawa, Y Kado, N Notoya, M Koizumi, S Ishikawa
Report of Aomori Prefectural Local Food Research Center (Japan), 2004
2004
Research and development of new processed foods
M Koizumi, S Ishikawa, N Notoya, Y Kado, K Osawa
Report of Aomori Prefectural Local Food Research Center (Japan), 2004
2004
Effect of calcium ion on gelation of meat of scallop (Patinopecten yessoensis)
Y Kado, N Notoya, K Osawa, M Koizumi, S Ishikawa
Report of Aomori Prefectural Local Food Research Center (Japan), 2004
2004
The system can't perform the operation now. Try again later.
Articles 1–20