Boltzmann Reinforcement Learning for Noise resilience in Analog Ising Machines
Published in arXiv preprint arXiv:2602.09162, 2026
Abstract:
Analog Ising machines (AIMs) have emerged as a promising paradigm for combinatorial optimization, utilizing physical dynamics to solve Ising problems with high energy efficiency. However, the performance of traditional optimization and sampling algorithms on these platforms is often limited by inherent measurement noise. We introduce BRAIN (Boltzmann Reinforcement for Analog Ising Networks), a distribution learning framework that utilizes variational reinforcement learning to approximate the Boltzmann distribution. By shifting from state-by-state sampling to aggregating information across multiple noisy measurements, BRAIN is resilient to Gaussian noise characteristic of AIMs. Under realistic 3% Gaussian measurement noise, BRAIN maintains 98% ground state fidelity, whereas Markov Chain Monte Carlo (MCMC) methods degrade to 51% fidelity. Our approach demonstrates how machine learning can enhance the robustness of analog optimization platforms, opening new possibilities for noise-resilient quantum-inspired computing.