All Papers

Shinsaku Sakaue, Taira Tsuchiya, Han Bao, Taihei Oki (2025). Online Inverse Linear Optimization: Improved Regret Bound, Robustness to Suboptimality, and Toward Tight Regret Analysis. arXiv [cs.LG].

Shinsaku Sakaue, Han Bao, Taira Tsuchiya (2025). Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis. International Conference on Artificial Intelligence and Statistics (AISTATS), to appear.

Han Bao, Shinsaku Sakaue (2025). Inverse Optimization with Prediction Market: A Characterization of Scoring Rules for Elciting System States. International Conference on Artificial Intelligence and Statistics (AISTATS), to appear.

Taihei Oki, Shinsaku Sakaue (2024). No-regret $\mathrm{M}^\natural$-concave function maximization: Stochastic bandit algorithms and NP-hardness of adversarial full-information setting. Advances in Neural Information Processing Systems (NeurIPS).

Shinsaku Sakaue, Taihei Oki (2024). Generalization bound and learning methods for data-driven projections in linear programming. Advances in Neural Information Processing Systems (NeurIPS).

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

Satoru Iwata, Taihei Oki, Shinsaku Sakaue (2023). Rate constant matrix contraction method for stiff master equations with detailed balance. arXiv [math.NA].

Taihei Oki, Shinsaku Sakaue (2023). Faster discrete convex function minimization with predictions: The $\mathrm{M}$-convex case. Advances in Neural Information Processing Systems (NeurIPS).

Shinsaku Sakaue, Taihei Oki (2023). Rethinking warm-starts with predictions: Learning predictions close to sets of optimal solutions for faster $\mathrm{L}$-/$\mathrm{L}^\natural$-convex function minimization. International Conference on Machine Learning (ICML).

Kazusato Oko, Shinsaku Sakaue, Shin‑ichi Tanigawa (2023). Nearly tight spectral sparsification of directed hypergraphs. International Colloquium on Automata, Languages, and Programming (ICALP).

Yoichi Chikahara, Shinsaku Sakaue, Akinori Fujino, Hisashi Kashima (2023). Making individually fair predictions with causal pathways. Data Mining and Knowledge Discovery.

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

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

Shinsaku Sakaue, Taihei Oki (2022). Sample complexity of learning heuristic functions for greedy-best-first and A* search. Advances in Neural Information Processing Systems (NeurIPS).

Shinichi Hemmi, Taihei Oki, Shinsaku Sakaue, Kaito Fujii, Satoru Iwata (2022). Lazy and fast greedy MAP inference for determinantal point process. Advances in Neural Information Processing Systems (NeurIPS).

Shinsaku Sakaue, Taihei Oki (2022). Discrete-convex-analysis-based framework for warm-starting algorithms with predictions. Advances in Neural Information Processing Systems (NeurIPS).

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

Kaito Fujii, Shinsaku Sakaue (2022). Algorithmic Bayesian persuasion with combinatorial actions. AAAI Conference on Artificial Intelligence (AAAI).

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

Shinsaku Sakaue, Kengo Nakamura (2021). Differentiable equilibrium computation with decision diagrams for Stackelberg models of combinatorial congestion games. Advances in Neural Information Processing Systems (NeurIPS).

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

Shinsaku Sakaue (2021). Differentiable greedy algorithm for monotone submodular maximization: Guarantees, gradient estimators, and applications. International Conference on Artificial Intelligence and Statistics (AISTATS).

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

Shinsaku Sakaue (2020). Guarantees of stochastic greedy algorithms for non-monotone submodular maximization with cardinality constraints. International Conference on Artificial Intelligence and Statistics (AISTATS).

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

Shinsaku Sakaue, Naoki Marumo (2019). Best-first search algorithm for non-convex sparse minimization. arXiv [cs.DS; math.OC].

Kaito Fujii, Shinsaku Sakaue (2019). Beyond adaptive submodularity: Approximation guarantees of greedy policy with adaptive submodularity ratio. International Conference on Machine Learning (ICML).

Shinsaku Sakaue (2019). Greedy and IHT algorithms for non-convex optimization with monotone costs of non-zeros. International Conference on Artificial Intelligence and Statistics (AISTATS).

Shinsaku Sakaue, Tsutomu Hirao, Masaaki Nishino, Masaaki Nagata (2018). Provable fast greedy compressive summarization with any monotone submodular function. North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL).

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

Shinsaku Sakaue, Masaaki Nishino, Norihito Yasuda (2018). Submodular function maximization over graphs via zero-suppressed binary decision diagrams. AAAI Conference on Artificial Intelligence (AAAI).

Shinsaku Sakaue, Masakazu Ishihata (2018). Accelerated best-first search with upper-bound computation for submodular function maximization. AAAI Conference on Artificial Intelligence (AAAI).

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

Shinsaku Sakaue (2017). On maximizing a monotone $k$-submodular function subject to a matroid constraint. Discrete Optimization.

Shinsaku Sakaue (2016). Using multiparameter eigenvalues for solving quadratic programming with quadratic equality constraints. Mathematical Engineering Technical Reports (METR).

Shinsaku Sakaue, Yuji Nakatsukasa, Akiko Takeda, Satoru Iwata (2016). Solving generalized CDT problems via two-parameter eigenvalues. SIAM Journal on Optimization.