arXiv:2608. 11648v1 Announce Type: cross Abstract: We study the power of quantum examples, as compared to classical examples, in the PAC learning framework.
arXiv:2607. 06472v1 Announce Type: cross Abstract: Given that quantum computers are naturally suited to simulate the behavior of quantum many-body systems, an immediate question arises: can one formulate physically motivated quantum machine learning (QML) tasks that exhibit learning separations?
Given that quantum computers are naturally suited to simulate the behavior of quantum many-body systems, an immediate question arises: can one formulate physically motivated quantum machine learning (QML) tasks that exhibit learning separations? We address this problem by studying the learnability of quantum many-body dynamics from the perspective of probably approximately correct (PAC)-learning.
The paper investigates whether having only forward access to a state-preparation unitary—without its inverse—can reduce the number of queries needed for quantum PAC learning. By analyzing worst-case scenarios over all compatible unitaries and finite dimensions, the authors prove that the optimal forward-only query complexities for realizable and agnostic learning are θ((d+log(1/δ))/ε) and θ((d+log(1/δ))/ε²), respectively, matching classical and quantum-copy bounds. These results demonstrate that forward-only access offers no asymptotic advantage over classical data or quantum copies, highlighting the essential role of inverse access for any improvement in the realizable setting.
arXiv:2602. 01177v3 Announce Type: replace-cross Abstract: We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms.
arXiv:2607. 01197v1 Announce Type: new Abstract: Quantum computing has emerged as a promising computational paradigm for machine learning (ML), with the potential to offer computational advantages over classical approaches.
The paper investigates whether a learner or tester with limited resources can improve performance by interacting with an untrusted, resource‑unconstrained party. It shows that for many scenarios, classical interaction offers no advantage, especially for memory‑constrained quantum algorithms. However, when quantum communication is permitted, interactive proof protocols enable memory‑constrained quantum verifiers to achieve significant gains through delegation.
arXiv:2604.07639v2 Announce Type: replace-cross Abstract: Broadly applicable quantum advantage, particularly in classical data processing and machine learning, has been a fundamental open problem. In...
arXiv:2609.38073v1 Announce Type: cross Abstract: We study exact learning with membership queries for concept classes $\mathcal C\subseteq\{0,1\}^N$, focusing on the relationships among their determi...
arXiv:2508. 19437v2 Announce Type: replace-cross Abstract: The importance of analyzing nontrivial datasets when testing quantum machine learning (QML) models is becoming increasingly prominent in literature, yet a cohesive framework for understanding dataset characteristics remains elusive.
arXiv:2606. 08276v1 Announce Type: cross Abstract: Quantum reinforcement learning (QRL) is a promising approach to learn effective decision strategies across several applications with stochastic environments.
The paper introduces Bernstein‑Vazirani Networks (BVNs), a non‑variational quantum machine‑learning framework that uses quantum interference for supervised learning. BVNs operate by placing labelled data into superposition and performing interference in the Fourier basis to extract globally informative features, and they can be generalized to use problem‑adapted bases for greater expressiveness. The authors demonstrate that BVNs can achieve universal function approximation with gradient‑free training, and report strong generalisation and competitive performance on synthetic and real‑world classification tasks as well as implicit image representation.
arXiv:2606. 11673v1 Announce Type: cross Abstract: Standard dot-product self-attention computes, in a single layer, only pairwise (order-2) interactions between tokens; representing a generic order-$k$ interaction is known to require either super-quadratic resources in one layer or composition across depth.