Kazuki Osawa - RankMe

24 papers A* 5A 1Journal 12Unranked 6

Year	Rank	Type	Title / Venue / Authors
2023	J	`jnl`	ASDL: A Unified Interface for Gradient Preconditioning in PyTorch. CoRR Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li, Torsten Hoefler
2023	J	`jnl`	Improving Continual Learning by Accurate Gradient Reconstructions of the Past. Trans. Mach. Learn. Res. Erik A. Daxberger, Siddharth Swaroop, Kazuki Osawa, Rio Yokota, Richard E. Turner, José Miguel Hernández-Lobato, Mohammad Emtiyaz Khan
2023	—	`conf`	PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices. MLSys Kazuki Osawa, Shigang Li, Torsten Hoefler
2023	A*	`conf`	Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. ICML Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
2022	A	`conf`	Efficient Quantized Sparse Matrix Operations on Tensor Cores. SC Shigang Li, Kazuki Osawa, Torsten Hoefler
2022	J	`jnl`	Efficient Quantized Sparse Matrix Operations on Tensor Cores. CoRR Shigang Li, Kazuki Osawa, Torsten Hoefler
2022	—	`conf`	Neural Graph Databases. LoG Maciej Besta, Patrick Iff, Florian Scheidl, Kazuki Osawa, Nikoli Dryden, Michal Podstawski, Tiancheng Chen, Torsten Hoefler
2022	J	`jnl`	Neural Graph Databases. CoRR Maciej Besta, Patrick Iff, Florian Scheidl, Kazuki Osawa, Nikoli Dryden, Michal Podstawski, Tiancheng Chen, Torsten Hoefler
2022	J	`jnl`	PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices. CoRR Kazuki Osawa, Shigang Li, Torsten Hoefler
2022	J	`jnl`	Scalable and Practical Natural Gradient for Large-Scale Deep Learning. IEEE Trans. Pattern Anal. Mach. Intell. Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota
2022	J	`jnl`	Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. CoRR Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
2020	J	`jnl`	Development of the Image-based Flight and Tree Measurement System in a Forest using a Drone. J. Robotics Netw. Artif. Life Keiji Kamei, Masahiro Kaneoka, Ken Yanai, Masaya Umemoto, Hiroki Yamaguchi, Kazuki Osawa
2020	A*	`conf`	Rich Information is Affordable: A Systematic Performance Analysis of Second-order Optimization Using K-FAC. KDD Yuichiro Ueno, Kazuki Osawa, Yohei Tsuji, Akira Naruse, Rio Yokota
2020	J	`jnl`	Scalable and Practical Natural Gradient for Large-Scale Deep Learning. CoRR Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota
2020	A*	`conf`	Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. NeurIPS Ryo Karakida, Kazuki Osawa
2020	J	`jnl`	Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. CoRR Ryo Karakida, Kazuki Osawa
2019	A*	`conf`	Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks. CVPR Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka
2019	—	`conf`	Performance Optimizations and Analysis of Distributed Deep Learning with Approximated Second-Order Optimization Method. ICPP Workshops Yohei Tsuji, Kazuki Osawa, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka
2019	A*	`conf`	Practical Deep Learning with Bayesian Principles. NeurIPS Kazuki Osawa, Siddharth Swaroop, Mohammad Emtiyaz Khan, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota
2019	J	`jnl`	Practical Deep Learning with Bayesian Principles. CoRR Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan
2018	J	`jnl`	Second-order Optimization Method for Large Mini-batch: Training ResNet-50 on ImageNet in 35 Epochs. CoRR Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka
2017	—	`conf`	Accelerating Matrix Multiplication in Deep Learning by Using Low-Rank Approximation. HPCS Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota
2017	—	`conf`	Evaluating the Compression Efficiency of the Filters in Convolutional Neural Networks. ICANN (2) Kazuki Osawa, Rio Yokota
2015	—	`conf`	Motion assistance apparatus enabled for neuro-rehabilitation of patients and for the promotion of exercise for the elderly. AIM Eiichirou Tanaka, Ryosuke Niwa, Kazuki Osawa, Keyaki Nakajima, Keiichi Muramatsu, Keiichi Watanuki, Shozo Saegusa, Louis Yuge