2 papers
quant-ph2025
Training Hybrid Quantum Policies with Classical Surrogates for Actor-Critic Reinforcement Learning
Jie Luo, Jeremy Kulcsar, Xueyin Chen +2
Reading out a parametrized quantum circuit through finite-shot measurements introduces a discrete stochastic component into hybrid quantum-classical neural networks, making gradien…
cs.DC2025
Federated Sinkhorn
Jeremy Kulcsar, Vyacheslav Kungurtsev, Georgios Korpas +2
We study distributed Sinkhorn iterations for entropy-regularized optimal transport when the Gibbs kernel operator is row-partitioned across c workers and cannot be centralized. We…