4 citations · 8 across the 7 of their papers we have counts for
7 papers
Slack-Free Deep-Unfolded Combinatorial Optimization Solver for Inequality Constraints
Ryo Hagiwara, Shunta Arai, Satoshi Takabe
Quantum annealing (QA) is used to solve combinatorial optimization problems (COPs). When COPs are implemented on quantum annealers, they are typically encoded as quadratic unconstr…
Physics-Aware Linearized ADMM and Its Unrolling
Satoshi Takabe, Shunta Arai, Tadashi Wadayama
Recently, partial differential equations (PDEs) have been used to directly model the measurement process in signal processing, although their evaluation is costly. In this paper, w…
Refined Gradient-Based Temperature Optimization for the Replica-Exchange Monte-Carlo Method
Tatsuya Miyata, Shunta Arai, Satoshi Takabe
The replica-exchange Monte-Carlo (RXMC) method is a powerful Markov-chain Monte-Carlo algorithm for sampling from multi-modal distributions, which are challenging for conventional…
Transfer Learning for Deep-Unfolded Combinatorial Optimization Solver with Quantum Annealer
Ryo Hagiwara, Shunta Arai, Satoshi Takabe
Quantum annealing (QA) has attracted research interest as a sampler and combinatorial optimization problem (COP) solver. A recently proposed sampling-based solver for QA significan…
Deep Unfolded Local Quantum Annealing
Shunta Arai, Satoshi Takabe
Local quantum annealing (LQA), an iterative algorithm, is designed to solve combinatorial optimization problems. It draws inspiration from QA, which utilizes adiabatic time evoluti…
Accelerating Convergence of Stein Variational Gradient Descent via Deep Unfolding
Yuya Kawamura, Satoshi Takabe
Stein variational gradient descent (SVGD) is a prominent particle-based variational inference method used for sampling a target distribution. SVGD has attracted interest for applic…
Convergence Acceleration of Markov Chain Monte Carlo-based Gradient Descent by Deep Unfolding
Ryo Hagiwara, Satoshi Takabe
This study proposes a trainable sampling-based solver for combinatorial optimization problems (COPs) using a deep-learning technique called deep unfolding. The proposed solver is b…