arXiv:2606. 20344v1 Announce Type: cross Abstract: Machine learning models have scaled to unprecedented sizes, making training across distributed devices the de facto standard in the field.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2602. 01177v3 Announce Type: replace-cross Abstract: We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms.
arXiv:2606. 01291v1 Announce Type: cross Abstract: Training Variational Quantum Circuits (VQCs) under Noisy Intermediate-Scale Quantum (NISQ) constraints introduces severe computational limitations: classical statevector simulation memory scales exponentially ($\mathcal{O}(2^n)$), and global cost functions suffer from barren plateaus where gradient variance decays exponentially ($\mathcal{O}(1/2^n)$).
arXiv:2608. 14995v1 Announce Type: cross Abstract: Quantum federated learning (QFL) lets multiple quantum clients collaboratively train quantum neural networks (QNNs) without sharing private local data.
arXiv:2607. 02444v1 Announce Type: cross Abstract: We study stabilizer state testing and learning with limited coherent quantum memory.
arXiv:2606. 12211v1 Announce Type: cross Abstract: A central principle in quantum machine learning is that an ansatz should be expressive enough to represent the quantum data of interest.
We study stabilizer state testing and learning with limited coherent quantum memory. Here an algorithm sequentially receives copies of an unknown $n$-qubit state, but may keep only $k$ qubits of coherent quantum memory between measurements.