LGNENov 29, 2022

Fast Hyperparameter Tuning for Ising Machines

arXiv:2211.15869v15 citationsh-index: 25
Originality Incremental advance
AI Analysis

This work addresses efficiency in hyperparameter tuning for Ising machines, which is incremental as it builds on existing TPE methods to speed up convergence.

The paper tackles the problem of slow hyperparameter tuning for Ising machines by proposing FastConvergence, a method that accelerates the Tree-structured Parzen Estimator (TPE) to reduce the number of trials needed, achieving similar results to TPE alone in less than half the trials on Traveling Salesman Problem and Quadratic Assignment Problem instances using Fujitsu's Digital Annealer.

In this paper, we propose a novel technique to accelerate Ising machines hyperparameter tuning. Firstly, we define Ising machine performance and explain the goal of hyperparameter tuning in regard to this performance definition. Secondly, we compare well-known hyperparameter tuning techniques, namely random sampling and Tree-structured Parzen Estimator (TPE) on different combinatorial optimization problems. Thirdly, we propose a new convergence acceleration method for TPE which we call "FastConvergence".It aims at limiting the number of required TPE trials to reach best performing hyperparameter values combination. We compare FastConvergence to previously mentioned well-known hyperparameter tuning techniques to show its effectiveness. For experiments, well-known Travel Salesman Problem (TSP) and Quadratic Assignment Problem (QAP) instances are used as input. The Ising machine used is Fujitsu's third generation Digital Annealer (DA). Results show, in most cases, FastConvergence can reach similar results to TPE alone within less than half the number of trials.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes