The paper investigates online learning of quantum states using logarithmic loss, a quantum analogue of online portfolio selection. It establishes a regret lower bound, proving that existing algorithms like Exponential Weights and Tseng et al. (2025) achieve optimal polynomial dependence on dimension. Leveraging this lower bound, the authors present a sample‑optimal quantum state tomography algorithm (up to polylogarithmic factors) and introduce a method for constructing confidence sequences for matrix‑valued random variables, with numerical results indicating competitive performance.
arXiv:2607. 01080v1 Announce Type: new Abstract: We investigate Gaussian process (GP) bandit optimization with quantum kernels, assuming the mean reward function lies in the reproducing kernel Hilbert space (RKHS) induced by the quantum kernel.
arXiv:2507. 22854v3 Announce Type: replace-cross Abstract: We propose novel classical and quantum online algorithms for learning finite- and infinite-horizon Markov Decision Processes (MDPs).
The paper introduces a classical algorithm that dequantizes a quantum sampler used for learning with optimized random features. By sampling heavy indices and reducing the transformation to a small principal block, the method produces a sparse classical representation with operator‑norm guarantees. This approach enables a classical sampler with specified accuracy and polynomial runtime, demonstrating that quantum block‑encoding factorizations can provide sufficient classical structure even when direct sampling access to the composite matrix is unavailable.
arXiv:2608. 14319v1 Announce Type: new Abstract: We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB) in the model of Wan et al.
arXiv:2607. 25492v2 Announce Type: replace Abstract: We study stochastic optimization with heavy-tailed gradient noise.
arXiv:2602. 18364v2 Announce Type: replace-cross Abstract: Maximum likelihood prediction (MLP) is a core task at the heart of modern large language models.
arXiv:2607. 10936v1 Announce Type: new Abstract: We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round $t = 1,\dots,T$, the adversary selects a $d \times d$ symmetric gain matrix $G_t$ with spectrum in $[0,1]$ and rank at most $r$; the learner simultaneously selects a unit vector $w_t \in S^{d-1}$ and receives the reward $w_t^\top G_t w_t$.
arXiv:2407.11473v2 Announce Type: replace Abstract: Maximum entropy inference and learning of graphical models are pivotal tasks in learning theory and optimization. This work extends algorithms for...
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:2606. 06316v1 Announce Type: cross Abstract: Financial crashes, cascading failures in infrastructure, and critical errors in AI systems are frequently triggered by events that occur with extremely small probability.
arXiv:2601.22005v2 Announce Type: replace-cross Abstract: Distance metrics are central to machine learning, yet distances between ensembles of quantum states remain poorly understood due to fundament...
arXiv:2608. 02826v1 Announce Type: cross Abstract: Reinforcement learning is a subfield of machine learning that studies how an agent interacts with an environment in order to extract as large a reward as possible.