Aki Dote
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Aki Dote has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Koji Hukushima
The University of Tokyo
3 shared publications - Ali Sheikholeslami
Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada
2 shared publications - Hirotaka Tamura
DXR Laboratory Inc., Yokohama 223-0066, Japan
2 shared publications - Jeffrey S. Rosenthal
University of Toronto
2 shared publications - Sigeng Chen
Department of Statistical Sciences University of Toronto 700 University Avenue M5G 1Z5 Toronto Ontario Canada
2 shared publications K. Hukushima
Graduate School of Arts and Sciences, The University of Tokyo - Komaba, Meguro-ku, Tokyo 153-8902, Japan
1 shared publication
Latest Publications
- Open Access
- 7 October 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 112 (4) , 045306
Ratio divergence learning using target energy in restricted Boltzmann machines: Beyond Kullback-Leibler divergence learning
We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning to restricted Boltzmann machines (RBMs), which are a minimal model that satisfies the universal approximation theorem for discrete distributions. RD learning combines the strength of both forward and reverse Kullback–Leibler divergence (KLD) learning, effectively addressing the “notorious” issues of underfitting with the forward KLD and mode collapse with the reverse KLD. Since the summation of forward and reverse KLD seems to be sufficient to combine the strength of both approaches, we include this learning method as a direct baseline in numerical experiments to evaluate its effectiveness. Numerical experiments demonstrate that RD learning outperforms other learning methods in terms of energy function fitting, mode-covering, and learning stability across various discrete energy-based models. Moreover, the performance gaps between RD learning and the other learning methods become more pronounced as the dimensions of target models increase.
- 7 October 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 112 (4) , 045306
Open AccessRatio divergence learning using target energy in restricted Boltzmann machines: Beyond Kullback-Leibler divergence learning
We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning to restricted Boltzmann machines (RBMs), which are a minimal model that satisfies the universal approximation theorem for discrete distributions. RD learning combines the strength of both forward and reverse Kullback–Leibler divergence (KLD) learning, effectively addressing the “notorious” issues of underfitting with the forward KLD and mode collapse with the reverse KLD. Since the summation of forward and reverse KLD seems to be sufficient to combine the strength of both approaches, we include this learning method as a direct baseline in numerical experiments to evaluate its effectiveness. Numerical experiments demonstrate that RD learning outperforms other learning methods in terms of energy function fitting, mode-covering, and learning stability across various discrete energy-based models. Moreover, the performance gaps between RD learning and the other learning methods become more pronounced as the dimensions of target models increase.
- Open Access
Ratio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback--Leibler Divergence Learning
We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning to restricted Boltzmann machines (RBMs), which are a minimal model that satisfies the universal approximation theorem for discrete distributions. RD learning combines the strength of both forward and reverse Kullback-Leibler divergence (KLD) learning, effectively addressing the "notorious" issues of underfitting with the forward KLD and mode-collapse with the reverse KLD. Since the summation of forward and reverse KLD seems to be sufficient to combine the strength of both approaches, we include this learning method as a direct baseline in numerical experiments to evaluate its effectiveness. Numerical experiments demonstrate that RD learning significantly outperforms other learning methods in terms of energy function fitting, mode-covering, and learning stability across various discrete energy-based models. Moreover, the performance gaps between RD learning and the other learning methods become more pronounced as the dimensions of target models increase.
Open AccessRatio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback--Leibler Divergence Learning
We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning to restricted Boltzmann machines (RBMs), which are a minimal model that satisfies the universal approximation theorem for discrete distributions. RD learning combines the strength of both forward and reverse Kullback-Leibler divergence (KLD) learning, effectively addressing the "notorious" issues of underfitting with the forward KLD and mode-collapse with the reverse KLD. Since the summation of forward and reverse KLD seems to be sufficient to combine the strength of both approaches, we include this learning method as a direct baseline in numerical experiments to evaluate its effectiveness. Numerical experiments demonstrate that RD learning significantly outperforms other learning methods in terms of energy function fitting, mode-covering, and learning stability across various discrete energy-based models. Moreover, the performance gaps between RD learning and the other learning methods become more pronounced as the dimensions of target models increase.
- 1 July 2024
- Published by IOP Publishing in Europhysics Letters
- Vol. 147 (1) , 11005
Effect of constraint relaxation on dynamic critical phenomena in minimum vertex cover problem
The effects of constraint relaxation on dynamic critical phenomena in the Minimum Vertex Cover (MVC) problem on Erdős-Rényi random graphs are investigated using Markov chain Monte Carlo simulations. Following our previous work that revealed the reduction of the critical temperature by constraint relaxation based on the penalty function method, this study focuses on investigating the critical properties of the relaxation time along its phase boundary. It is found that the dynamical correlation function of MVC with respect to the problem size and the constraint strength follows a universal scaling function. The analysis shows that the relaxation time decreases as the constraints are relaxed. This decrease is more pronounced for the critical amplitude than for the critical exponent, and this result is interpreted in terms of the system's microscopic energy barriers due to the constraint relaxation.
- 1 July 2024
- Published by IOP Publishing in Europhysics Letters
- Vol. 147 (1) , 11005
Effect of constraint relaxation on dynamic critical phenomena in minimum vertex cover problem
The effects of constraint relaxation on dynamic critical phenomena in the Minimum Vertex Cover (MVC) problem on Erdős-Rényi random graphs are investigated using Markov chain Monte Carlo simulations. Following our previous work that revealed the reduction of the critical temperature by constraint relaxation based on the penalty function method, this study focuses on investigating the critical properties of the relaxation time along its phase boundary. It is found that the dynamical correlation function of MVC with respect to the problem size and the constraint strength follows a universal scaling function. The analysis shows that the relaxation time decreases as the constraints are relaxed. This decrease is more pronounced for the critical amplitude than for the critical exponent, and this result is interpreted in terms of the system's microscopic energy barriers due to the constraint relaxation.
- 5 April 2024
- Published by American Physical Society (APS) in Physical Review E
- Vol. 109 (4) , 044304
Effect of constraint relaxation on the minimum vertex cover problem in random graphs
A statistical-mechanical study of the effect of constraint relaxation on the minimum vertex cover problem in Erdős-Rényi random graphs is presented. Using a penalty-method formulation for constraint relaxation, typical properties of solutions, including infeasible solutions that violate the constraints, are analyzed by means of the replica method and cavity method. The problem involves a competition between reducing the number of vertices to be covered and satisfying the edge constraints. The analysis under the replica-symmetric (RS) ansatz clarifies that the competition leads to degeneracies in the vertex and edge states, which determine the quantitative properties of the system, such as the cover and penalty ratios. A precise analysis of these effects improves the accuracy of RS approximation for the minimum cover ratio in the replica symmetry-breaking (RSB) region. Furthermore, the analysis based on the RS cavity method indicates that the RS/RSB boundary of the ground states with respect to the mean degree of the graphs is expanded, and the critical temperature is lowered by constraint relaxation.
- 5 April 2024
- Published by American Physical Society (APS) in Physical Review E
- Vol. 109 (4) , 044304
Effect of constraint relaxation on the minimum vertex cover problem in random graphs
A statistical-mechanical study of the effect of constraint relaxation on the minimum vertex cover problem in Erdős-Rényi random graphs is presented. Using a penalty-method formulation for constraint relaxation, typical properties of solutions, including infeasible solutions that violate the constraints, are analyzed by means of the replica method and cavity method. The problem involves a competition between reducing the number of vertices to be covered and satisfying the edge constraints. The analysis under the replica-symmetric (RS) ansatz clarifies that the competition leads to degeneracies in the vertex and edge states, which determine the quantitative properties of the system, such as the cover and penalty ratios. A precise analysis of these effects improves the accuracy of RS approximation for the minimum cover ratio in the replica symmetry-breaking (RSB) region. Furthermore, the analysis based on the RS cavity method indicates that the RS/RSB boundary of the ground states with respect to the mean degree of the graphs is expanded, and the critical temperature is lowered by constraint relaxation.
- 5 October 2023
- Published by Springer Nature in Statistics and Computing
- Vol. 33 (6) , 1-17
Optimization via Rejection-Free Partial Neighbor Search
- 5 October 2023
- Published by Springer Nature in Statistics and Computing
- Vol. 33 (6) , 1-17
Optimization via Rejection-Free Partial Neighbor Search
- Open Access
Optimization via Rejection-Free Partial Neighbor Search
Simulated Annealing using Metropolis steps at decreasing temperatures is widely used to solve complex combinatorial optimization problems. In order to improve its efficiency, we can use the Rejection-Free version of the Metropolis algorithm, which avoids the inefficiency of rejections by considering all the neighbors at every step. As a solution to avoid the algorithm from becoming stuck in local extreme areas, we propose an enhanced version of Rejection-Free called Partial Neighbor Search (PNS), which only considers random parts of the neighbors while applying Rejection-Free. We demonstrate the superior performance of the Rejection-Free PNS algorithm by applying these methods to several examples, such as the QUBO question, the Knapsack problem, the 3R3XOR problem, and the quadratic programming.
Open AccessOptimization via Rejection-Free Partial Neighbor Search
Simulated Annealing using Metropolis steps at decreasing temperatures is widely used to solve complex combinatorial optimization problems. In order to improve its efficiency, we can use the Rejection-Free version of the Metropolis algorithm, which avoids the inefficiency of rejections by considering all the neighbors at every step. As a solution to avoid the algorithm from becoming stuck in local extreme areas, we propose an enhanced version of Rejection-Free called Partial Neighbor Search (PNS), which only considers random parts of the neighbors while applying Rejection-Free. We demonstrate the superior performance of the Rejection-Free PNS algorithm by applying these methods to several examples, such as the QUBO question, the Knapsack problem, the 3R3XOR problem, and the quadratic programming.