arXiv subjects

Ayanava Dasgupta

Publications and source records attributed to Ayanava Dasgupta.

7 recordsLinked to original sources

arXiv2026

Haar-Bayesian Pure-State Prediction under Relative-Entropy Loss: Arbitrary-Effect Reduction and Global Optimality

We study Haar-Bayesian prediction of one unmeasured copy of an unknown finite-dimensional pure quantum state after an arbitrary collective measurement on $n$ observed copies. Performance is evaluated by quantum relative entropy. For a fixed measurement, the Bayes predictive state is the posterior mean and the optimized conditional loss is its entropy. We then optimize the measurement over all POVMs on the symmetric subspace. For every nonzero positive effect $E$, the corresponding posterior predictive state is $μ_E=(I+nρ_E)/(n+d)$, where $ρ_E$ is the normalized one-particle marginal of $E$. Since a pure spectrum majorizes every density-operator spectrum, this identity gives an outcome-wise entropy lower bound. Coherent rank-one effects attain the bound, and their Haar orbit yields the highest-weight covariant POVM. Hence this POVM is globally Bayes optimal over all collective measurements and, by covariance, globally minimax. Its exact risk is $h_d((n+1)/(n+d))$, where $h_d(r)=-r\log r-(1-r)\log((1-r)/(d-1))$. The same arbitrary-effect reduction shows that the highest-weight POVM also maximizes the joint overlap between the latent pure state and its posterior predictive state, equivalently the mean posterior purity, with optimum $((n+1)^2+d-1)/(n+d)^2$.

quant-ph↗

arXiv2026

Uniqueness and Cramér-Rao Efficiency of Quantum U-Statistics

We study unbiased estimation of scalar-valued polynomial functionals of quantum states from independent copies. We establish an equivalence between the first-order marginal of a permutation-invariant finite-copy observable and the functional gradient. We then prove that, among unbiased permutation-invariant estimators, the quantum U-statistic is the unique extension to an arbitrary number of copies. We further derive a universal variance expansion in which the leading $1/n$ term is determined by the variance of the functional gradient, while higher-order contributions are of order $O(1/n^2)$. This leading variance coincides with the multiparameter quantum Cramér-Rao limit, establishing asymptotic efficiency of quantum U-statistics. We also characterize the higher-order scaling at points where the variance of the first-order gradient vanishes. As an application, we analyze the Bures $χ^2$-divergence and show that a spectral lower bound on the reference state is sufficient but not necessary for bounded-variance estimation.

quant-ph↗

arXiv2026

Privacy Implies Stability: Information-Theoretic Generalization Bounds for Quantum Learning

We develop an information-theoretic framework connecting stability, privacy, and generalization for quantum learning algorithms. Learning procedures are modeled as quantum instruments with classical-quantum outputs, and losses are represented by observables. We prove that under a classical-quantum sub-Gaussian condition, an information-theoretic stability measure controls the expected generalization error. Furthermore, we establish a high-probability generalization bound using quantum Rényi divergences to manage higher-order dependencies under non-commutativity. In the trusted Data Processor setting, quantum differential privacy (QDP) provides a mechanism for stability. We show that one-neighbor QDP strictly bounds the information leaked by the classical-quantum output. Combining this with our stability theorem yields a direct privacy-to-generalization guarantee. We also explore an untrusted Data Processor setting. Here, output privacy alone is insufficient since an adversarial processor could perform a highly informative procedure before applying noisy post-processing. To combat this, we introduce Information-Theoretic Admissibility (ITA), a certification condition ensuring the prescribed procedure is not just a degraded version of a strictly more informative, physically allowed operation on the encoded ensemble. We prove a fundamental separation: while admissibility and privacy are in strong tension in classical models, quantum non-orthogonality makes them compatible. A quantum measurement can be ITA - exhausting all relevant accessible information - without perfectly recovering the classical dataset. We illustrate this separation through a concrete quantum ITA example.

quant-ph↗

arXiv2026

Quantum Information Ordering and Differential Privacy

We study quantum differential privacy (QDP) by defining a notion of the order of informativeness between pairs of quantum states. In particular, we show that if the hypothesis testing divergence of one pair dominates over that of the other pair, then this dominance holds for every $f$-divergence. This approach completely characterizes $(\varepsilon,δ)$-QDP mechanisms by identifying the most informative $(\varepsilon,δ)$-DP quantum state pairs. We apply this to study precise limits for privatized hypothesis testing and privatized quantum parameter estimation, including tight upper-bounds on the quantum Fisher information under QDP. Finally, we establish near-optimal contraction bounds for differentially private quantum channels with respect to the hockey-stick divergence.

quant-ph↗

arXiv2025

Generalization Bounds for Quantum Learning via Rényi Divergences

This work advances the theoretical understanding of quantum learning by establishing a new family of upper bounds on the expected generalization error of quantum learning algorithms, leveraging the framework introduced by Caro et al. (2024) and a new definition for the expected true loss. Our primary contribution is the derivation of these bounds in terms of quantum and classical Rényi divergences, utilizing a variational approach for evaluating quantum Rényi divergences, specifically the Petz and a newly introduced modified sandwich quantum Rényi divergence. Analytically and numerically, we demonstrate the superior performance of the bounds derived using the modified sandwich quantum Rényi divergence compared to those based on the Petz divergence. Furthermore, we provide probabilistic generalization error bounds using two distinct techniques: one based on the modified sandwich quantum Rényi divergence and classical Rényi divergence, and another employing smooth max Rényi divergence.

quant-ph↗

arXiv2025

Intersection and union of subspaces with applications to communication over authenticated classical-quantum channels and composite hypothesis testing

In information theory, we often use intersection and union of the typical sets to analyze various communication problems. However, in the quantum setting it is not very clear how to construct a measurement which behaves analogously to intersection and union of the typical sets. In this work, we construct a projection operator which behaves very similarly to intersection and union of the typical sets. Our construction relies on the Jordan's lemma. Using this construction we study the problem of communication over authenticated classical-quantum channels and derive its capacity. As another application of our construction, we also study the problem of quantum asymmetric composite hypothesis testing.

cs.IT↗

arXiv2024

Universal tester for multiple independence testing and classical-quantum arbitrarily varying multiple access channel

We study two kinds of different problems. One is the multiple independence testing, which can be considered as a kind of generalization of quantum Stein's lemma. We test whether the quantum system is correlated to the classical system or is independent of it. Here, the null hypothesis is composed of states having the quantum system is correlated to the classical system in an arbitrarily varying form. The second problem is the problem of reliable communication over classical-quantum arbitrarily varying multiple access channels (CQ-AVMAC) and establishing its capacity region by giving multiple achievability techniques. We prove that each of these techniques is optimal by proving a converse. Further, for both these techniques, the decoder designed is a \emph{universal} decoder and can achieve any rate pair in the capacity region without time sharing and also these decoders do not depend on the channel and therefore they are universal. Our result covers the case when the channel parameter is continuous, which has not been studied even in the classical case. Further, both these techniques can be easily generalized to the case when there are $T (T>2)$ senders. The design of each of these decoders is based on the study of multiple independence testing. This approach allows us to study the problem of reliable communication over CQ-AVMAC from the point of view of hypothesis testing. Further, we also give a necessary and sufficient condition for the deterministic code capacity region of CQ-AVMAC to be non-empty.

quant-ph↗