More Like this

1. Minimax estimation of low-rank quantum states and their linear functionals

   https://doi.org/10.3150/23-BEJ1610  

   Lahiry, Samriddha; Nussbaum, Michael (February 2024, Bernoulli)

   In classical statistics, a well known paradigm consists in establishing asymptotic equivalence between an experiment of i.i.d. observations and a Gaussian shift experiment, with the aim of obtaining optimal estimators in the former complicated model from the latter simpler model. In particular, a statistical experiment consisting of n i.i.d. observations from d-dimensional multinomial distributions can be well approximated by an experiment consisting of d − 1 dimensional Gaussian distributions. In a quantum version of the result, it has been shown that a collection of n qudits (d-dimensional quantum states) of full rank can be well approximated by a quantum system containing a classical part, which is a d − 1 dimensional Gaussian distribution, and a quantum part containing an ensemble of d(d − 1)/2 shifted thermal states. In this paper, we obtain a generalization of this result when the qudits are not of full rank. We show that when the rank of the qudits is r, then the limiting experiment consists of an r − 1 dimensional Gaussian distribution and an ensemble of both shifted pure and shifted thermal states. For estimation purposes, we establish an asymptotic minimax result in the limiting Gaussian model. Analogous results are then obtained for estimation of a low rank qudit from an ensemble of identically prepared, independent quantum systems, using the local asymptotic equivalence result. We also consider the problem of estimation of a linear functional of the quantum state. We construct an estimator for the functional, analyze the risk and use quantum local asymptotic equivalence to show that our estimator is also optimal in the minimax sense. 

   more » « less
2. Fluctuations of subgraph counts in graphon based random graphs

   https://doi.org/10.1017/S0963548322000335  

   Bhattacharya, Bhaswar B.; Chatterjee, Anirban; Janson, Svante (May 2023, Combinatorics, Probability and Computing)

   Abstract Given a graphon $$W$$ and a finite simple graph $$H$$ , with vertex set $V(H)$ , denote by $$X_n(H, W)$$ the number of copies of $$H$$ in a $$W$$ -random graph on $$n$$ vertices. The asymptotic distribution of $$X_n(H, W)$$ was recently obtained by Hladký, Pelekis, and Šileikis [17] in the case where $$H$$ is a clique. In this paper, we extend this result to any fixed graph $$H$$ . Towards this we introduce a notion of $$H$$ -regularity of graphons and show that if the graphon $$W$$ is not $$H$$ -regular, then $$X_n(H, W)$$ has Gaussian fluctuations with scaling $$n^{|V(H)|-\frac{1}{2}}$$ . On the other hand, if $$W$$ is $$H$$ -regular, then the fluctuations are of order $$n^{|V(H)|-1}$$ and the limiting distribution of $$X_n(H, W)$$ can have both Gaussian and non-Gaussian components, where the non-Gaussian component is a (possibly) infinite weighted sum of centred chi-squared random variables with the weights determined by the spectral properties of a graphon derived from $$W$$ . Our proofs use the asymptotic theory of generalised $$U$$ -statistics developed by Janson and Nowicki [22]. We also investigate the structure of $$H$$ -regular graphons for which either the Gaussian or the non-Gaussian component of the limiting distribution (but not both) is degenerate. Interestingly, there are also $$H$$ -regular graphons $$W$$ for which both the Gaussian or the non-Gaussian components are degenerate, that is, $$X_n(H, W)$$ has a degenerate limit even under the scaling $$n^{|V(H)|-1}$$ . We give an example of this degeneracy with $$H=K_{1, 3}$$ (the 3-star) and also establish non-degeneracy in a few examples. This naturally leads to interesting open questions on higher order degeneracies. 

   more » « less
3. Edge Distribution of Thinned Real Eigenvalues in the Real Ginibre Ensemble

   https://doi.org/10.1007/s00023-022-01182-0  

   Baik, Jinho; Bothner, Thomas (April 2022, Annales Henri Poincaré)

   Abstract This paper is concerned with the explicit computation of the limiting distribution function of the largest real eigenvalue in the real Ginibre ensemble when each real eigenvalue has been removed independently with constant likelihood. We show that the recently discovered integrable structures in [2] generalize from the real Ginibre ensemble to its thinned equivalent. Concretely, we express the aforementioned limiting distribution function as a convex combination of two simple Fredholm determinants and connect the same function to the inverse scattering theory of the Zakharov–Shabat system. As corollaries, we provide a Zakharov–Shabat evaluation of the ensemble’s real eigenvalue generating function and obtain precise control over the limiting distribution function’s tails. The latter part includes the explicit computation of the usually difficult constant factors. 

   more » « less
4. Computing the Tracy-Widom Distribution for Arbitrary $$\beta>0$$

   https://doi.org/10.3842/SIGMA.2024.005  

   Trogdon, Thomas; Zhang, Yiting (January 2024, Symmetry, Integrability and Geometry: Methods and Applications)

   We compute the Tracy-Widom distribution describing the asymptotic distribution of the largest eigenvalue of a large random matrix by solving a boundary-value problem posed by Bloemendal in his Ph.D. Thesis (2011). The distribution is computed in two ways. The first method is a second-order finite-difference method and the second is a highly accurate Fourier spectral method. Since $$\beta$$ is simply a parameter in the boundary-value problem, any $$\beta> 0$$ can be used, in principle. The limiting distribution of the $$n$$th largest eigenvalue can also be computed. Our methods are available in the Julia package TracyWidomBeta.jl. 

   more » « less
5. Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

   Kumar, Aounon; Levine, Alexander; Goldstein, Tom; Feizi, Soheil (January 2020, International Conference on Machine Learning (ICML))

   null (Ed.)

   Randomized smoothing, using just a simple isotropic Gaussian distribution, has been shown to produce good robustness guarantees against ℓ2-norm bounded adversaries. In this work, we show that extending the smoothing technique to defend against other attack models can be challenging, especially in the high-dimensional regime. In particular, for a vast class of i.i.d.~smoothing distributions, we prove that the largest ℓp-radius that can be certified decreases as O(1/d12−1p) with dimension d for p>2. Notably, for p≥2, this dependence on d is no better than that of the ℓp-radius that can be certified using isotropic Gaussian smoothing, essentially putting a matching lower bound on the robustness radius. When restricted to {\it generalized} Gaussian smoothing, these two bounds can be shown to be within a constant factor of each other in an asymptotic sense, establishing that Gaussian smoothing provides the best possible results, up to a constant factor, when p≥2. We present experimental results on CIFAR to validate our theory. For other smoothing distributions, such as, a uniform distribution within an ℓ1 or an ℓ∞-norm ball, we show upper bounds of the form O(1/d) and O(1/d1−1p) respectively, which have an even worse dependence on d. 

   more » « less