• case-insensitive prefix search: default
  e.g., sig matches "SIGIR" as well as "signal"
• exact word search: append dollar sign ($) to word
  e.g., graph$ matches "graph", but not "graphics"
• boolean and: separate words by space
  e.g., codd model
• boolean or: connect words by pipe symbol (|)
  e.g., graph|network

Update May 7, 2017: Please note that we had to disable the phrase search operator (.) and the boolean not operator (-) due to technical problems. For the time being, phrase search queries will yield regular prefix search result, and search terms preceded by a minus will be interpreted as regular (positive) search terms.

found 25 matches

• 2023
• 
  Erik A. Daxberger, Siddharth Swaroop, Kazuki Osawa, Rio Yokota, Richard E. Turner, José Miguel Hernández-Lobato, Mohammad Emtiyaz Khan:
  Improving Continual Learning by Accurate Gradient Reconstructions of the Past. Trans. Mach. Learn. Res. 2023 (2023)
• 
  Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa:
  Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. ICML 2023: 15809-15827
• 
  Yoshinobu Kano, Neo Watanabe, Kaito Kagaminuma, Claus Aranha, Jaewon Lee, Benedek Hauer, Hisaichi Shibata, Soichiro Miki, Yuta Nakamura, Takuya Okubo, Soga Shigemura, Rei Ito, Kazuki Takashima, Tomoki Fukuda, Masahiro Wakutani, Tomoya Hatanaka, Mami Uchida, Mikio Abe, Akihiro Mikami, Takashi Otsuki, Zhiyang Qi, Kei Harada, Michimasa Inaba, Daisuke Katagami, Hirotaka Osawa, Fujio Toriumi:
  AIWolfDial 2023: Summary of Natural Language Division of 5th International AIWolf Contest. INLG (Generation Challenges) 2023: 84-100
• 
  Kazuki Osawa, Shigang Li, Torsten Hoefler:
  PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices. MLSys 2023
• 
  Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li, Torsten Hoefler:
  ASDL: A Unified Interface for Gradient Preconditioning in PyTorch. CoRR abs/2305.04684 (2023)
• 2022
• 
  Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota:
  Scalable and Practical Natural Gradient for Large-Scale Deep Learning. IEEE Trans. Pattern Anal. Mach. Intell. 44(1): 404-415 (2022)
• 
  Maciej Besta, Patrick Iff, Florian Scheidl, Kazuki Osawa, Nikoli Dryden, Michal Podstawski, Tiancheng Chen, Torsten Hoefler:
  Neural Graph Databases. LoG 2022: 31
• 
  Shigang Li, Kazuki Osawa, Torsten Hoefler:
  Efficient Quantized Sparse Matrix Operations on Tensor Cores. SC 2022: 37:1-37:15
• 
  Shigang Li, Kazuki Osawa, Torsten Hoefler:
  Efficient Quantized Sparse Matrix Operations on Tensor Cores. CoRR abs/2209.06979 (2022)
• 
  Maciej Besta, Patrick Iff, Florian Scheidl, Kazuki Osawa, Nikoli Dryden, Michal Podstawski, Tiancheng Chen, Torsten Hoefler:
  Neural Graph Databases. CoRR abs/2209.09732 (2022)
• 
  Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa:
  Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. CoRR abs/2210.02720 (2022)
• 
  Kazuki Osawa, Shigang Li, Torsten Hoefler:
  PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices. CoRR abs/2211.14133 (2022)
• 2020
• 
  Keiji Kamei, Masahiro Kaneoka, Ken Yanai, Masaya Umemoto, Hiroki Yamaguchi, Kazuki Osawa:
  Development of the Image-based Flight and Tree Measurement System in a Forest using a Drone. J. Robotics Netw. Artif. Life 7(2): 86-90 (2020)
• 
  Yuichiro Ueno, Kazuki Osawa, Yohei Tsuji, Akira Naruse, Rio Yokota:
  Rich Information is Affordable: A Systematic Performance Analysis of Second-order Optimization Using K-FAC. KDD 2020: 2145-2153
• 
  Ryo Karakida, Kazuki Osawa:
  Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. NeurIPS 2020
• 
  Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota:
  Scalable and Practical Natural Gradient for Large-Scale Deep Learning. CoRR abs/2002.06015 (2020)
• 
  Ryo Karakida, Kazuki Osawa:
  Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. CoRR abs/2010.00879 (2020)
• 2019
• 
  Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka:
  Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks. CVPR 2019: 12359-12367
• 
  Yohei Tsuji, Kazuki Osawa, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka:
  Performance Optimizations and Analysis of Distributed Deep Learning with Approximated Second-Order Optimization Method. ICPP Workshops 2019: 21:1-21:8
• 
  Kazuki Osawa, Siddharth Swaroop, Mohammad Emtiyaz Khan, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota:
  Practical Deep Learning with Bayesian Principles. NeurIPS 2019: 4289-4301
• 
  Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan:
  Practical Deep Learning with Bayesian Principles. CoRR abs/1906.02506 (2019)
• 2018
• 
  Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka:
  Second-order Optimization Method for Large Mini-batch: Training ResNet-50 on ImageNet in 35 Epochs. CoRR abs/1811.12019 (2018)
• 2017
• 
  Kazuki Osawa, Rio Yokota:
  Evaluating the Compression Efficiency of the Filters in Convolutional Neural Networks. ICANN (2) 2017: 459-466
• 
  Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota:
  Accelerating Matrix Multiplication in Deep Learning by Using Low-Rank Approximation. HPCS 2017: 186-192
• 2015
• 
  Eiichirou Tanaka, Ryosuke Niwa, Kazuki Osawa, Keyaki Nakajima, Keiichi Muramatsu, Keiichi Watanuki, Shozo Saegusa, Louis Yuge:
  Motion assistance apparatus enabled for neuro-rehabilitation of patients and for the promotion of exercise for the elderly. AIM 2015: 937-942