Publications

Yoichi Chikahara, Shinsaku Sakaue, Akinori Fujino, and Hisashi Kashima. Making individually fair predictions with causal pathways, Data Mining and Knowledge Discovery, 37, pp. 327–1373, 2023.

Han Bao, Shinsaku Sakaue. Sparse regularized optimal transport with deformed q-entropy, Entropy, 24(11), 1634, 2022.

Tomohiro Nakamura, Shinsaku Sakaue, Kaito Fujii, Yu Harabuchi, Satoshi Maeda, and Satoru Iwata. Selecting molecules with diverse structures and properties by maximizing submodular functions of descriptors learned with graph neural networks, Scientific Reports, 12, 1124, 2022.

Shinsaku Sakaue. On maximizing a monotone k-submodular function subject to a matroid constraint, Discrete Optimization, 23, pp. 105–113, 2017.

Shinsaku Sakaue, Akiko Takeda, Sunyoung Kim, and Naoki Ito. Exact semidefinite programming relaxations with truncated moment matrix for binary polynomial optimization problems, SIAM Journal on Optimization, 27(1), pp. 565–582, 2017.

Shinsaku Sakaue, Yuji Nakatsukasa, Akiko Takeda, and Satoru Iwata. Solving generalized CDT problems via two-parameter eigenvalues, SIAM Journal on Optimization, 26(3), pp. 1669–1694, 2016.

Taihei Oki and Shinsaku Sakaue. No-regret M♮-concave function maximization: Stochastic bandit algorithms and NP-hardness of adversarial full-information setting, The 38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024. (to appear)

Shinsaku Sakaue and Taihei Oki. Generalization bound and learning methods for data-driven projections in linear programming, The 38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024. (to appear)

Shinsaku Sakaue, Han Bao, Taira Tsuchiya, and Taihei Oki. Online structured prediction with Fenchel–Young losses and improved surrogate regret for online multiclass classification with logistic loss, The 37th Annual Conference on Learning Theory (COLT 2024), pp. 4458–4486, 2024.

Taihei Oki and Shinsaku Sakaue. Faster discrete convex function minimization with predictions: The M-convex case, The 37th Conference on Neural Information Processing Systems (NeurIPS 2023), pp. 68576–68588, 2023.

Shinsaku Sakaue and Taihei Oki. Rethinking warm-starts with predictions: Learning predictions close to sets of optimal solutions for faster L-/L♮-convex function minimization, The 40th International Conference on Machine Learning (ICML 2023), pp. 29760-29776, 2023.

Kazusato Oko, Shinsaku Sakaue, and Shin-ichi Tanigawa. Nearly tight spectral sparsification of directed hypergraphs, The 50th International Colloquium on Automata, Languages, and Programming (ICALP 2023), pp. 94:1–94:19, 2023.

Shinsaku Sakaue and Taihei Oki. Improved generalization bound and learning of sparsity patterns for data-driven low-rank approximation, The 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), pp. 1–10, 2023.

Shinichi Hemmi, Taihei Oki, Shinsaku Sakaue, Kaito Fujii, and Satoru Iwata. Lazy and fast greedy MAP inference for determinantal point process, The 36th Conference on Neural Information Processing Systems (NeurIPS 2022), pp. 2776–2789, 2022.

Shinsaku Sakaue and Taihei Oki. Discrete-convex-analysis-based framework for warm-starting algorithms with predictions, The 36th Conference on Neural Information Processing Systems (NeurIPS 2022), pp. 20988–21000, 2022.

Shinsaku Sakaue and Taihei Oki. Sample complexity of learning heuristic functions for greedy-best-first and A* search, The 36th Conference on Neural Information Processing Systems (NeurIPS 2022), pp. 2889–2901, 2022.

Ryoma Onaka, Kengo Nakamura, Takeru Inoue, Masaaki Nishino, Norihito Yasuda, and Shinsaku Sakaue. Exact and scalable network reliability evaluation for probabilistic correlated failures, The 2022 IEEE Global Communications Conference (GLOBECOM 2022), pp. 5547–5552, 2022.

Kaito Fujii and Shinsaku Sakaue. Algorithmic Bayesian persuasion with combinatorial actions, The 36th AAAI Conference on Artificial Intelligence (AAAI 2022), pp. 5016–5024, 2022.

Shinsaku Sakaue and Kengo Nakamura. Differentiable equilibrium computation with decision diagrams for Stackelberg models of combinatorial congestion games, The 35th Conference on Neural Information Processing Systems (NeurIPS 2021), pp. 9416–9428, 2021.

Shinsaku Sakaue. Differentiable greedy algorithm for monotone submodular maximization: Guarantees, gradient estimators, and applications, The 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021), pp. 28–36, 2021.

Yoichi Chikahara, Shinsaku Sakaue, Akinori Fujino, and Hisashi Kashima. Learning individually fair classifier with path-specific causal-effect constraint, The 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021), pp. 145–153, 2021.

Shinsaku Sakaue. On maximization of weakly modular functions: Guarantees of multi-stage algorithms, tractability, and hardness, The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020), pp. 22–33, 2020.

Shinsaku Sakaue. Guarantees of stochastic greedy algorithms for non-monotone submodular maximization with cardinality constraint, The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020), pp. 11–21, 2020.

Kengo Nakamura, Shinsaku Sakaue, and Norihito Yasuda. Practical Frank–Wolfe method with decision diagrams for computing Wardrop equilibrium of combinatorial congestion games, The 34th AAAI Conference on Artificial Intelligence (AAAI 2020), pp. 2200–2209, 2020.

Kaito Fujii and Shinsaku Sakaue. Beyond adaptive submodularity: Approximation guarantees of greedy policy with adaptive submodularity ratio, The 36th International Conference on Machine Learning (ICML 2019), 2042–2051, 2019.

Shinsaku Sakaue. Greedy and IHT algorithms for non-convex optimization with monotone costs of non-zeros, The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), pp. 206–215, 2019.

Shinsaku Sakaue, Tsutomu Hirao, Masaaki Nishino, and Masaaki Nagata. Provable fast greedy compressive summarization with any monotone submodular function, The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2018), pp. 1737–1746, 2018.

Shinsaku Sakaue, Masakazu Ishihata, and Shin-ichi Minato. Efficient bandit combinatorial optimization algorithm with zero-suppressed binary decision diagrams, The 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018), pp. 585–594, 2018.

Shinsaku Sakaue and Masakazu Ishihata. Accelerated best-first search with upper-bound computation for submodular function maximization, The 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), pp. 1413–1421, 2018.

Shinsaku Sakaue, Masaaki Nishino, and Norihito Yasuda. Submodular function maximization over graphs via zero-suppressed binary decision diagrams, The 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), pp. 1422–1430, 2018.

Satoru Iwata, Taihei Oki, and Shinsaku Sakaue. Rate constant matrix contraction method for stiff master equations with detailed balance, arXiv preprints, arXiv:2312.05470, 2023.

Shinsaku Sakaue and Naoki Marumo. Best-first search algorithm for non-convex sparse minimization, arXiv preprints, arXiv:1910.01296, 2019.

Shinsaku Sakaue. Using multiparameter eigenvalues for solving quadratic programming with quadratic equality constraints, Mathematical Engineering Technical Reports, METR 2016-02, 2016.