Nobuo Yamashita
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nobuo Yamashita has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Ellen Hidemi Fukuda
Graduate School of Informatics, Kyoto University, Kyoto, Japan
6 shared publications - Kenji Ueda
Advanced Technology R&D Center, Mitsubishi Electric Corporation, Hyogo, Japan
3 shared publications - Hardik Tankaria
Department of Applied Mathematics and Physics, Graduate School of Informatics, Kyoto University, Kyoto, Japan
2 shared publications - Hiroki Tanabe
Yahoo Japan
2 shared publications - Shota Yamanaka
Department of Applied Mathematics and Physics Graduate School of Informatics Kyoto University 606-8501 Kyoto Japan
2 shared publications - Yan Gu
School of Mathematics Nanjing University of Aeronautics and Astronautics 210016 Nanjing China
2 shared publications
Latest Publications
- Open Access
A strong second-order sequential optimality condition for nonlinear programming problems
Most numerical methods developed for solving nonlinear programming problems are designed to find points that satisfy certain optimality conditions. While the Karush-Kuhn-Tucker conditions are well-known, they become invalid when constraint qualifications (CQ) are not met. Recent advances in sequential optimality conditions address this limitation in both first- and second-order cases, providing genuine optimality guarantees at local optima, even when CQs do not hold. However, some second-order sequential optimality conditions still require some restrictive conditions on constraints in the recent literature. In this paper, we propose a new strong second-order sequential optimality condition without CQs. We also show that a penalty-type method and an augmented Lagrangian method generate points satisfying these new optimality conditions.
Open AccessA strong second-order sequential optimality condition for nonlinear programming problems
Most numerical methods developed for solving nonlinear programming problems are designed to find points that satisfy certain optimality conditions. While the Karush-Kuhn-Tucker conditions are well-known, they become invalid when constraint qualifications (CQ) are not met. Recent advances in sequential optimality conditions address this limitation in both first- and second-order cases, providing genuine optimality guarantees at local optima, even when CQs do not hold. However, some second-order sequential optimality conditions still require some restrictive conditions on constraints in the recent literature. In this paper, we propose a new strong second-order sequential optimality condition without CQs. We also show that a penalty-type method and an augmented Lagrangian method generate points satisfying these new optimality conditions.
- 1 January 2025
- Published by Chongqing Normal University in Pacific Journal of Optimization
- p. 35
A strong second-order sequential optimality condition for nonlinear programming problems
(Communicated by Liqun Qi) Dedicated to Professor Terry Rockafellar on the occasion of his 90th birthday Most numerical methods developed for solving nonlinear programming problems are designed to find points that satisfy certain optimality conditions. While the Karush-Kuhn-Tucker conditions are well-known, they become invalid when constraint qualifications (CQ) are not met. Recent advances in sequential optimality conditions address this limitation in both first- and second-order cases, providing genuine optimality guarantees at local optima, even when CQs do not hold. However, some second-order sequential optimality conditions still require some restrictive conditions on constraints in the recent literature. In this paper, we propose a new strong second-order sequential optimality condition without CQs. We also show that a penalty-type method and an augmented Lagrangian method generate points satisfying these new optimality conditions.
- 1 January 2025
- Published by Chongqing Normal University in Pacific Journal of Optimization
- p. 35
A strong second-order sequential optimality condition for nonlinear programming problems
(Communicated by Liqun Qi) Dedicated to Professor Terry Rockafellar on the occasion of his 90th birthday Most numerical methods developed for solving nonlinear programming problems are designed to find points that satisfy certain optimality conditions. While the Karush-Kuhn-Tucker conditions are well-known, they become invalid when constraint qualifications (CQ) are not met. Recent advances in sequential optimality conditions address this limitation in both first- and second-order cases, providing genuine optimality guarantees at local optima, even when CQs do not hold. However, some second-order sequential optimality conditions still require some restrictive conditions on constraints in the recent literature. In this paper, we propose a new strong second-order sequential optimality condition without CQs. We also show that a penalty-type method and an augmented Lagrangian method generate points satisfying these new optimality conditions.
- Open Access
- 14 March 2024
- Published by Springer Nature
- p. 3-7
Advanced Mathematical Science for Mobility Society
The automotive industry has made steady progress in technological innovations under the names of Connected-Autonomous/Automated-Shared-Electric (CASE) and Mobility as a Service (MaaS). Needless to say, mathematics and informatics are important to support such innovations. As the concept of cars and movement itself is diversifying, they are indispensable for grasping the essence of the future mobility society and building the foundation for the next generation. Based on this idea, research unit named “Advanced Mathematical Science for Mobility Society” was established at Kyoto University as a base for envisioning a future mobility society in collaboration with researchers led by Toyota Motor Corporation and Kyoto University. In this chapter, we briefly discuss the motivation of the project as well as its research directions.
- 14 March 2024
- Published by Springer Nature
- p. 3-7
Open AccessAdvanced Mathematical Science for Mobility Society
The automotive industry has made steady progress in technological innovations under the names of Connected-Autonomous/Automated-Shared-Electric (CASE) and Mobility as a Service (MaaS). Needless to say, mathematics and informatics are important to support such innovations. As the concept of cars and movement itself is diversifying, they are indispensable for grasping the essence of the future mobility society and building the foundation for the next generation. Based on this idea, research unit named “Advanced Mathematical Science for Mobility Society” was established at Kyoto University as a base for envisioning a future mobility society in collaboration with researchers led by Toyota Motor Corporation and Kyoto University. In this chapter, we briefly discuss the motivation of the project as well as its research directions.
- 1 January 2024
- Published by Chongqing Normal University in Pacific Journal of Optimization
- Vol. 20 (4) , 12-826
A proximal gradient method with Bregman distance in multi-objective optimization
(Communicated by Liqun Qi) A multi-objective proximal gradient method was proposed recently as a suitable descent method for composite multi-objective optimization problems. However, the method solves subproblems using only Euclidean distances, and it requires the differentiable part of each objective to have a Lipschitz continuous gradient, which limits its application. In this paper, we propose an extension of this method, by using Bregman distances and requiring a less demanding assumption called relative smoothness. We also consider two stepsize strategies: the constant stepsize and the backtracking procedure. In both cases, we prove global convergence in the sense of Pareto stationarity and analyze the convergence rate through a merit function.
- 1 January 2024
- Published by Chongqing Normal University in Pacific Journal of Optimization
- Vol. 20 (4) , 12-826
A proximal gradient method with Bregman distance in multi-objective optimization
(Communicated by Liqun Qi) A multi-objective proximal gradient method was proposed recently as a suitable descent method for composite multi-objective optimization problems. However, the method solves subproblems using only Euclidean distances, and it requires the differentiable part of each objective to have a Lipschitz continuous gradient, which limits its application. In this paper, we propose an extension of this method, by using Bregman distances and requiring a less demanding assumption called relative smoothness. We also consider two stepsize strategies: the constant stepsize and the backtracking procedure. In both cases, we prove global convergence in the sense of Pareto stationarity and analyze the convergence rate through a merit function.
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Journal of Industrial and Management Optimization
- Vol. 20 (2) , 525-547
A stochastic variance reduced gradient using Barzilai-Borwein techniques as second order information
In this paper, we consider improving the stochastic variance reduce gradient (SVRG) method by incorporating the curvature information of the objective function. We propose to reduce the variance of stochastic gradients using the computationally efficient Barzilai-Borwein (BB) method by incorporating it into the SVRG. We also incorporate a BB-step size as a variant. We show linear convergence to not only the proposed method but also the other existing SVRG variants that use second-order information. We conduct the numerical experiments on the benchmark datasets and demonstrate that the proposed method with a constant step size outperforms the existing variance reduced methods for some test problems.
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Journal of Industrial and Management Optimization
- Vol. 20 (2) , 525-547
A stochastic variance reduced gradient using Barzilai-Borwein techniques as second order information
In this paper, we consider improving the stochastic variance reduce gradient (SVRG) method by incorporating the curvature information of the objective function. We propose to reduce the variance of stochastic gradients using the computationally efficient Barzilai-Borwein (BB) method by incorporating it into the SVRG. We also incorporate a BB-step size as a variant. We show linear convergence to not only the proposed method but also the other existing SVRG variants that use second-order information. We conduct the numerical experiments on the benchmark datasets and demonstrate that the proposed method with a constant step size outperforms the existing variance reduced methods for some test problems.
- 9 June 2023
- Published by Springer Nature in Computational Optimization and Applications
- Vol. 86 (2) , 421-455
An accelerated proximal gradient method for multiobjective optimization
- 9 June 2023
- Published by Springer Nature in Computational Optimization and Applications
- Vol. 86 (2) , 421-455
An accelerated proximal gradient method for multiobjective optimization
- Open Access
Monotonicity for Multiobjective Accelerated Proximal Gradient Methods
Accelerated proximal gradient methods, which are also called fast iterative shrinkage-thresholding algorithms (FISTA) are known to be efficient for many applications. Recently, Tanabe et al. proposed an extension of FISTA for multiobjective optimization problems. However, similarly to the single-objective minimization case, the objective functions values may increase in some iterations, and inexact computations of subproblems can also lead to divergence. Motivated by this, here we propose a variant of the FISTA for multiobjective optimization, that imposes some monotonicity of the objective functions values. In the single-objective case, we retrieve the so-called MFISTA, proposed by Beck and Teboulle. We also prove that our method has global convergence with rate $O(1/k^2)$, where $k$ is the number of iterations, and show some numerical advantages in requiring monotonicity.Open AccessMonotonicity for Multiobjective Accelerated Proximal Gradient Methods
Accelerated proximal gradient methods, which are also called fast iterative shrinkage-thresholding algorithms (FISTA) are known to be efficient for many applications. Recently, Tanabe et al. proposed an extension of FISTA for multiobjective optimization problems. However, similarly to the single-objective minimization case, the objective functions values may increase in some iterations, and inexact computations of subproblems can also lead to divergence. Motivated by this, here we propose a variant of the FISTA for multiobjective optimization, that imposes some monotonicity of the objective functions values. In the single-objective case, we retrieve the so-called MFISTA, proposed by Beck and Teboulle. We also prove that our method has global convergence with rate $O(1/k^2)$, where $k$ is the number of iterations, and show some numerical advantages in requiring monotonicity. - 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Journal of Industrial and Management Optimization
- Vol. 19 (11) , 7826-7848
A dual active set method for $ \ell $1-regularized problem
We consider an $ \ell $1-regularized problem, which has many applications such as compressed sensing, MRI, and seismic images. Although there have been some methods for the problem, they cannot obtain a highly accurate solution. To overcome this drawback, we propose a dual active set method, which is an active set method for the Fenchel dual problem of the $ \ell $1-regularized problem. Our method finds a highly accurate solution quickly because of the following features of the dual problem: (i) the dimension of the decision variables is smaller; (ii) since the optimal solution of the primal problem is sparse, the active constraints of the optimal solution of the dual problem are few and can be identified quickly. Then, we show that the method outputs the solution with finite iterations when it solves certain subproblems exactly. Moreover, we give its efficient and concrete implementation for Basis Pursuit Denoising (BPDN), which is a typical $ \ell $1-regularized problem. In numerical experiments for BPDN, our method provides more accurate solutions than all baselines in comparable computing time.- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Journal of Industrial and Management Optimization
- Vol. 19 (11) , 7826-7848
A dual active set method for $ \ell $1-regularized problem
We consider an $ \ell $1-regularized problem, which has many applications such as compressed sensing, MRI, and seismic images. Although there have been some methods for the problem, they cannot obtain a highly accurate solution. To overcome this drawback, we propose a dual active set method, which is an active set method for the Fenchel dual problem of the $ \ell $1-regularized problem. Our method finds a highly accurate solution quickly because of the following features of the dual problem: (i) the dimension of the decision variables is smaller; (ii) since the optimal solution of the primal problem is sparse, the active constraints of the optimal solution of the dual problem are few and can be identified quickly. Then, we show that the method outputs the solution with finite iterations when it solves certain subproblems exactly. Moreover, we give its efficient and concrete implementation for Basis Pursuit Denoising (BPDN), which is a typical $ \ell $1-regularized problem. In numerical experiments for BPDN, our method provides more accurate solutions than all baselines in comparable computing time.- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Journal of Industrial and Management Optimization
- Vol. 19 (9) , 6430-6450
Two-stage distributionally robust noncooperative games: Existence of Nash equilibrium and its application to Cournot–Nash competition
Two-stage distributionally robust stochastic noncooperative games with continuous decision variables are studied. In such games, each player solves a two-stage distributionally robust optimization problem depending on the decisions of the other players. Existing studies in this area have been limited with strict assumptions, such as linear decision rules, and supposed that each player solves a two-stage linear distributionally robust optimization with a specifically structured ambiguity set. This limitation motivated us to generalize and analyze the game in a nonlinear case. The contributions of this study are (ⅰ) demonstrating the conditions for the existence of two-stage Nash equilibria under convexity and compactness assumptions, and (ⅱ) consideration of a two-stage distributionally robust Cournot–Nash competition as an application, as well as an investigation into the conditions for the existence of market equilibria in an economic sense. We also report some results of numerical experiments to illustrate how distributional robustness affects the decision of each player in the Cournot–Nash competition.
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Journal of Industrial and Management Optimization
- Vol. 19 (9) , 6430-6450
Two-stage distributionally robust noncooperative games: Existence of Nash equilibrium and its application to Cournot–Nash competition
Two-stage distributionally robust stochastic noncooperative games with continuous decision variables are studied. In such games, each player solves a two-stage distributionally robust optimization problem depending on the decisions of the other players. Existing studies in this area have been limited with strict assumptions, such as linear decision rules, and supposed that each player solves a two-stage linear distributionally robust optimization with a specifically structured ambiguity set. This limitation motivated us to generalize and analyze the game in a nonlinear case. The contributions of this study are (ⅰ) demonstrating the conditions for the existence of two-stage Nash equilibria under convexity and compactness assumptions, and (ⅱ) consideration of a two-stage distributionally robust Cournot–Nash competition as an application, as well as an investigation into the conditions for the existence of market equilibria in an economic sense. We also report some results of numerical experiments to illustrate how distributional robustness affects the decision of each player in the Cournot–Nash competition.
- 24 April 2022
- Published by Springer Nature in Optimization Letters
- Vol. 17 (2) , 333-350
Convergence rates analysis of a multiobjective proximal gradient method
- 24 April 2022
- Published by Springer Nature in Optimization Letters
- Vol. 17 (2) , 333-350
Convergence rates analysis of a multiobjective proximal gradient method