Classical and quantum kernel fusion for two-sample testing

The paper introduces MMD-FUSE, a two-sample test that remains effective on small datasets by fusing classical and quantum kernels. By combining the inductive biases of classical kernels with the expressive power of quantum kernels, the hybrid approach achieves higher test power, especially for small, high‑dimensional data. Experiments on synthetic and real clinical datasets confirm that the method consistently outperforms purely classical counterparts and adapts robustly to varied data characteristics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• rag