フォロー
Takuya Akiba
Takuya Akiba
Sakana AI
確認したメール アドレス: sakana.ai - ホームページ
タイトル
引用先
引用先
Optuna: A next-generation hyperparameter optimization framework
T Akiba, S Sano, T Yanase, T Ohta, M Koyama
Proceedings of the 25th ACM SIGKDD international conference on knowledge …, 2019
45342019
Fast exact shortest-path distance queries on large networks by pruned landmark labeling
T Akiba, Y Iwata, Y Yoshida
Proceedings of the 2013 ACM SIGMOD International Conference on Management of …, 2013
4542013
Extremely large minibatch sgd: Training resnet-50 on imagenet in 15 minutes
T Akiba, S Suzuki, K Fukuda
arXiv preprint arXiv:1711.04325, 2017
3732017
Adversarial attacks and defences competition
A Kurakin, I Goodfellow, S Bengio, Y Dong, F Liao, M Liang, T Pang, ...
The NIPS'17 Competition: Building Intelligent Systems, 195-231, 2018
3352018
Fast and accurate influence maximization on large networks with pruned monte-carlo simulations
N Ohsaka, T Akiba, Y Yoshida, K Kawarabayashi
Proceedings of the AAAI conference on artificial intelligence 28 (1), 2014
2202014
Shakedrop regularization for deep residual learning
Y Yamada, M Iwamura, T Akiba, K Kise
IEEE Access 7, 186126-186136, 2019
1672019
Branch-and-reduce exponential/FPT algorithms in practice: A case study of vertex cover
T Akiba, Y Iwata
Theoretical Computer Science 609, 211-225, 2016
1652016
Chainer: A deep learning framework for accelerating the research cycle
S Tokui, R Okuta, T Akiba, Y Niitani, T Ogawa, S Saito, S Suzuki, ...
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019
1572019
Fast shortest-path distance queries on road networks by pruned highway labeling
T Akiba, Y Iwata, K Kawarabayashi, Y Kawata
2014 Proceedings of the sixteenth workshop on algorithm engineering and …, 2014
1202014
Dynamic and historical shortest-path distance queries on large evolving networks by pruned landmark labeling
T Akiba, Y Iwata, Y Yoshida
Proceedings of the 23rd international conference on World wide web, 237-248, 2014
1192014
Dynamic influence analysis in evolving networks
N Ohsaka, T Akiba, Y Yoshida, K Kawarabayashi
Proceedings of the VLDB Endowment 9 (12), 1077-1088, 2016
972016
Shortest-path queries for complex networks: exploiting low tree-width outside the core
T Akiba, C Sommer, K Kawarabayashi
Proceedings of the 15th International Conference on Extending Database …, 2012
972012
Computing personalized pagerank quickly by exploiting graph structures
T Maehara, T Akiba, Y Iwata, K Kawarabayashi
Proceedings of the VLDB Endowment 7 (12), 1023-1034, 2014
902014
ChainerMN: Scalable distributed deep learning framework
T Akiba, K Fukuda, S Suzuki
arXiv preprint arXiv:1710.11351, 2017
872017
Fast and scalable reachability queries on graphs by pruned labeling with landmarks and paths
Y Yano, T Akiba, Y Iwata, Y Yoshida
Proceedings of the 22nd ACM international conference on Information …, 2013
862013
Variance-based gradient compression for efficient distributed deep learning
Y Tsuzuku, H Imachi, T Akiba
arXiv preprint arXiv:1802.06058, 2018
732018
Linear-time enumeration of maximal k-edge-connected subgraphs in large networks by random contraction
T Akiba, Y Iwata, Y Yoshida
Proceedings of the 22nd ACM international conference on Information …, 2013
712013
Fully dynamic betweenness centrality maintenance on massive networks
T Hayashi, T Akiba, Y Yoshida
Proceedings of the VLDB Endowment 9 (2), 48-59, 2015
632015
Optuna: a next-generation hyperparameter optimization framework (2019)
T Akiba, S Sano, T Yanase, T Ohta, M Koyama
arXiv preprint arXiv:1907.10902 9, 1907
511907
A graph theoretic framework of recomputation algorithms for memory-efficient backpropagation
M Kusumoto, T Inoue, G Watanabe, T Akiba, M Koyama
Advances in Neural Information Processing Systems 32, 2019
432019
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20