Kazuki Osawa

According to our database, Kazuki Osawa authored at least 16 papers between 2015 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

ASDL: A Unified Interface for Gradient Preconditioning in PyTorch.

Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li, Torsten Hoefler

CoRR, 2023

Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias.

Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa

Proceedings of the International Conference on Machine Learning, 2023

2022

Scalable and Practical Natural Gradient for Large-Scale Deep Learning.

Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota

IEEE Trans. Pattern Anal. Mach. Intell., 2022

PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices.

Kazuki Osawa, Shigang Li, Torsten Hoefler

CoRR, 2022

Efficient Quantized Sparse Matrix Operations on Tensor Cores.

Shigang Li, Kazuki Osawa, Torsten Hoefler

Proceedings of the SC22: International Conference for High Performance Computing, 2022

Neural Graph Databases.

Maciej Besta, Patrick Iff, Florian Scheidl, Kazuki Osawa, Nikoli Dryden, Michal Podstawski, Tiancheng Chen, Torsten Hoefler

Proceedings of the Learning on Graphs Conference, 2022

2020

Development of the Image-based Flight and Tree Measurement System in a Forest using a Drone.

Keiji Kamei, Masahiro Kaneoka, Ken Yanai, Masaya Umemoto, Hiroki Yamaguchi, Kazuki Osawa

J. Robotics Netw. Artif. Life, 2020

Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks.

Ryo Karakida, Kazuki Osawa

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Rich Information is Affordable: A Systematic Performance Analysis of Second-order Optimization Using K-FAC.

Yuichiro Ueno, Kazuki Osawa, Yohei Tsuji, Akira Naruse, Rio Yokota

Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

2019

Practical Deep Learning with Bayesian Principles.

Kazuki Osawa, Siddharth Swaroop, Mohammad Emtiyaz Khan, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Performance Optimizations and Analysis of Distributed Deep Learning with Approximated Second-Order Optimization Method.

Yohei Tsuji, Kazuki Osawa, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka

Proceedings of the 48th International Conference on Parallel Processing, 2019

Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks.

Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018

Second-order Optimization Method for Large Mini-batch: Training ResNet-50 on ImageNet in 35 Epochs.

Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka

CoRR, 2018

2017

Accelerating Matrix Multiplication in Deep Learning by Using Low-Rank Approximation.

Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota

Proceedings of the 2017 International Conference on High Performance Computing & Simulation, 2017

Evaluating the Compression Efficiency of the Filters in Convolutional Neural Networks.

Kazuki Osawa, Rio Yokota

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2017, 2017

2015

Motion assistance apparatus enabled for neuro-rehabilitation of patients and for the promotion of exercise for the elderly.

Eiichirou Tanaka, Ryosuke Niwa, Kazuki Osawa, Keyaki Nakajima, Keiichi Muramatsu, Keiichi Watanuki, Shozo Saegusa, Louis Yuge

Proceedings of the IEEE International Conference on Advanced Intelligent Mechatronics, 2015