Abstract In many quantum tasks, there is an unknown quantum object that one wishes to learn. An online strategy for this task involves adaptively refining a hypothesis to reproduce such an object or its measurement statistics. A common evaluation metric for such a strategy is its regret, or roughly the accumulated errors in hypothesis statistics. We prove a sublinear regret bound for learning over general subsets of positive semidefinite matrices via the regularized-follow-the-leader algorithm and apply it to various settings where one wishes to learn quantum objects. For concrete applications, we present a sublinear regret bound for learning quantum states, effects, channels, interactive measurements, strategies, co-strategies, and the collection of inner products of pure states. Our bound applies to many other quantum objects with compact, convex representations. In proving our regret bound, we establish various matrix analysis results useful in quantum information theory. This includes a generalization of Pinsker’s inequality for arbitrary positive semidefinite operators with possibly different traces, which may be of independent interest and applicable to more general classes of divergences.
Abstract In many quantum tasks, there is an unknown quantum object that one wishes to learn. An online strategy for this task involves adaptively refining a hypothesis to reproduce such an object or its measurement statistics. A common evaluation metric for such a strategy is its regret, or roughly the accumulated errors in hypothesis statistics. We prove a sublinear regret bound for learning over general subsets of positive semidefinite matrices via the regularized-follow-the-leader algorithm and apply it to various settings where one wishes to learn quantum objects. For concrete applications, we present a sublinear regret bound for learning quantum states, effects, channels, interactive measurements, strategies, co-strategies, and the collection of inner products of pure states. Our bound applies to many other quantum objects with compact, convex representations. In proving our regret bound, we establish various matrix analysis results useful in quantum information theory. This includes a generalization of Pinsker’s inequality for arbitrary positive semidefinite operators with possibly different traces, which may be of independent interest and applicable to more general classes of divergences.
Online learning is a framework for interfacing with environments whose structure is revealed through interactions; quantum information theory is a means of representing data and its processing consistent with modern understanding of physics. Their union is symbiotic---sequential processing is light on precious quantum resources, and quantum algorithms can surpass known bounds of classical algorithms---their combination being an area of independent interest. This thesis aims to exemplify the above point via five case studies on tomography, change detection, and function evaluation. In the process of deriving efficient tomography procedures, prior work has shown that quantum states can be learned in online adversarial environments. We extend this notion to subsets of positive semidefinite operators, including general quantum objects such as states, measurements, channels, strategies, co-strategies, and Gram matrices. We tailor a regularized follow-the-leader algorithm and achieve sublinear regret. As a byproduct, we show a generalization of Pinsker's inequality that accounts for differences in trace, its proof method more broadly applicable to general divergences. We further extend online learnability to objects in arbitrary physical theories. We derive mappings between Euclidean Jordan algebras and generalized probabilistic theories, using methods for the former to show that states in the latter are learnable. Specifically, we develop a projective version of the symmetric cone multiplicative weights update algorithm that achieves sublinear regret when learning states of generalized probabilistic theories. We consider the task of detecting changes in sequences of unknown quantum states with a constraint of no false positives, developing efficient and optimal online quantum algorithms. These include online algorithms with small amounts of quantum memory based on the swap test, and optimal algorithms projecting onto the symmetric subspace. We find circuit constructions for these algorithms, analyze their complexity, and show their equivalence under certain memory limitations. The proposed algorithms are applicable to quality control and anomaly detection in quantum devices, and may be of independent interest for identity testing and optimal cloning. We elaborate on the quality control aspect of changepoint methods by developing procedures for aiding the calibration of near-term quantum devices. These consist of algorithms for certification and changepoint detection in Hamiltonian dynamics, which enable continuous monitoring and trigger recalibration procedures. Using a cumulative sum procedure, we attain an asymptotically-optimal scaling of the average times to detection versus false positive, dependent primarily on Hamiltonian norm bounds. Lastly, we quantify the effect of memory limits on Boolean function evaluation of quantum sequences---a task applicable to distributed sensing and quantum reading of classical memories, among others. We show that minimum-error function evaluation in the memoryless regime is equivalent to the so-called pretty good measurement and hence shares its performance guarantee. Additionally, we characterize the precise set of functions on which this strategy performs optimally---affine functions. The above studies reveal insights about learnability as a universal property and the tradeoffs between performance and resource requirements in online settings, informing the choice of quantum settings best-suited for online learning. We conclude by summarizing these takeaways, along with listing remaining open questions.
The problem of efficient quantum state learning, also called shadow tomography, aims to comprehend an unknown d -dimensional quantum state through POVMs. Yet, these states are rarely static; they evolve due to factors such as measurements, environmental noise, or inherent Hamiltonian state transitions. This paper leverages techniques from adaptive online learning to keep pace with such state changes.The key metrics considered for learning in these mutable environments are enhanced notions of regret, specifically adaptive and dynamic regret. We present adaptive and dynamic regret bounds for online shadow tomography, which are polynomial in the number of qubits and sublinear in the number of measurements. To support our theoretical findings, we include numerical experiments that validate our proposed models.
We study the problem of online learning of quantum states with logarithmic loss, which is a quantum generalization of online portfolio selection and has applications to quantum state tomography, the task of estimating an unknown quantum state from measurement outcomes. We first establish a regret lower bound, showing that the regret rates of Exponential Weights and the algorithm of Tseng et al. (2025) have optimal polynomial dependence on the dimension. Our analysis leads to two further results. First, our lower-bound proof leads to a quantum state tomography algorithm that is sample optimal up to polylogarithmic factors in the sample size. Second, we develop an algorithm for constructing confidence sequences for the mean of a matrix-valued random variable. A numerical experiment shows that the latter algorithm is competitive with existing methods.
Abstract Suppose we have many copies of an unknown n -qubit state . We measure some copies of using a known two-outcome measurement E 1 , then other copies using a measurement E 2 , and so on. At each stage t , we generate a current hypothesis about the state , using the outcomes of the previous measurements. We show that it is possible to do this in a way that guarantees that , the error in our prediction for the next measurement, is at least at most times. Even in the ‘non-realizable’ setting—where there could be arbitrary noise in the measurement outcomes—we show how to output hypothesis states that incur at most excess loss over the best possible state on the first T measurements. These results generalize a 2007 theorem by Aaronson on the PAC-learnability of quantum states, to the online and regret-minimization settings. We give three different ways to prove our results—using convex optimization, quantum postselection, and sequential fat-shattering dimension—which have different advantages in terms of parameters and portability.
This thesis studies the exploration and exploitation trade-off in online learning of properties of quantum states using multi-armed bandits. Given streaming access to an unknown quantum state, in each round we select an observable from a set of actions to maximize its expectation value. Using past information, we refine actions to minimize regret; the cumulative gap between current reward and the maximum possible. We derive information-theoretic lower bounds and optimal strategies with matching upper bounds, showing regret typically scales as the square root of rounds. As an application, we reframe quantum state tomography to both learn the state efficiently and minimize measurement disturbance. For pure states and continuous actions, we achieve polylogarithmic regret using a sample-optimal algorithm based on a weighted online least squares estimator. The algorithm relies on the optimistic principle and controls the eigenvalues of the design matrix. We also apply our framework to quantum recommender systems and thermodynamic work extraction from unknown states. In this last setting, our results demonstrate an exponential advantage in work dissipation over tomography-based protocols.
Two-party adversarial interactions are of fundamental importance in the study of cryptography and machine learning, as they allow us to work in dynamic environments to model and adapt to various challenges, fostering reliability and robustness. In this thesis, we first consider such interactions in the domain of information-theoretic cryptography, where we propose new protocols and security bounds involving various two-party primitives such as coin flipping, bit commitment, and variants of oblivious transfer. We begin by developing the mathematical framework of stochastic selection, which is potentially useful for devising new protocols with improved security for a combination of various tasks. We then use this idea to develop the first protocols for Rabin oblivious transfer that offer partial information-theoretic security and also provide a non-trivial lower bound on its security. We also relax some of the more commonly used assumptions to consider the security of protocols in broader compositions and independently, allowing for devices that may be potentially malicious. In the former setting, we demonstrate that the weak coin flipping task -- which enjoys almost perfect standalone security -- may not be immune to attacks when used in larger compositions. In the latter, we establish the impossibility of determining the inner workings of a shared quantum mechanical device -- a phenomenon commonly known as self-testing -- in the presence of an adversary. Finally, we consider a slightly different task in a similar setting, where we discuss the classical online learnability of various quantum objects. We prove a sublinear regret bound for learning over general subsets of positive semidefinite matrices via the regularized follow-the-leader algorithm and apply it to various settings involving the learning of quantum objects. For concrete applications, we present a sublinear regret bound for learning quantum states, effects, channels, interactive measurements, strategies, co-strategies, and collections of inner products of pure states. In proving our regret bound, we establish various matrix analysis results useful in quantum information theory, including a generalization of Pinsker's inequality for arbitrary positive semidefinite operators with possibly different traces, which may be of independent interest in the study of more general classes of divergences.