arXiv subjects

Ujan Gangopadhyay

Publications and source records attributed to Ujan Gangopadhyay.

6 recordsLinked to original sources

arXiv2023

Learning Networks from Gaussian Graphical Models and Gaussian Free Fields

We investigate the problem of estimating the structure of a weighted network from repeated measurements of a Gaussian Graphical Model (GGM) on the network. In this vein, we consider GGMs whose covariance structures align with the geometry of the weighted network on which they are based. Such GGMs have been of longstanding interest in statistical physics, and are referred to as the Gaussian Free Field (GFF). In recent years, they have attracted considerable interest in the machine learning and theoretical computer science. In this work, we propose a novel estimator for the weighted network (equivalently, its Laplacian) from repeated measurements of a GFF on the network, based on the Fourier analytic properties of the Gaussian distribution. In this pursuit, our approach exploits complex-valued statistics constructed from observed data, that are of interest on their own right. We demonstrate the effectiveness of our estimator with concrete recovery guarantees and bounds on the required sample complexity. In particular, we show that the proposed statistic achieves the parametric rate of estimation for fixed network size. In the setting of networks growing with sample size, our results show that for Erdos-Renyi random graphs $G(d,p)$ above the connectivity threshold, we demonstrate that network recovery takes place with high probability as soon as the sample size $n$ satisfies $n \gg d^4 \log d \cdot p^{-2}$.

math.ST↗

arXiv2023

Approximate Gibbsian structure in strongly correlated point fields and generalized Gaussian zero ensembles

Gibbsian structure in random point fields has been a classical tool for studying their spatial properties. However, exact Gibbs property is available only in a relatively limited class of models, and it does not adequately address many random fields with a strongly dependent spatial structure. In this work, we provide a general framework for approximate Gibbsian structure for strongly correlated random point fields. These include processes that exhibit strong spatial rigidity, in particular, a certain one-parameter family of analytic Gaussian zero point fields, namely the $α$-GAFs. Our framework entails conditions that may be verified via finite particle approximations to the process, a phenomenon that we call an approximate Gibbs property. We show that these enable one to compare the spatial conditional measures in the infinite volume limit with Gibbs-type densities supported on appropriate singular manifolds, a phenomenon we refer to as a generalized Gibbs property. We demonstrate the scope of our approach by showing that a generalized Gibbs property holds with a logarithmic pair potential for the $α$-GAFs for any value of $α$. This establishes the level of rigidity of the $α$-GAF zero process to be exactly $\lfloor \frac{1}α \rfloor$, settling in the affirmative an open question regarding the existence of point processes with any specified level of rigidity. For processes such as the zeros of $α$-GAFs, which involve complex, many-body interactions, our results imply that the local behaviour of the random points still exhibits 2D Coulomb-type repulsion in the short range. Our techniques can be leveraged to estimate the relative energies of configurations under local perturbations, with possible implications for dynamics and stochastic geometry on strongly correlated random point fields.

math.PR↗

arXiv2022

Almost Sure Convergence of Randomized Urn Models with Application to Elephant Random Walk

We consider a randomized urn model with objects of finitely many colors. The replacement matrices are random, and are conditionally independent of the color chosen given the past. Further, the conditional expectations of the replacement matrices are close to an almost surely irreducible matrix. We obtain almost sure and $L^1$ convergence of the configuration vector, the proportion vector and the count vector. We show that first moment is sufficient for i.i.d.\ replacement matrices independent of past color choices. This significantly improves the similar results for urn models obtained in Athreya and Ney (1972) requiring $L\log_+ L$ moments. For more general adaptive sequence of replacement matrices, a little more than $L\log_+ L$ condition is required. Similar results based on $L^1$ moment assumption alone has been considered independently and in parallel in Zhang (2018). Finally, using the result, we study a delayed elephant random walk on the nonnegative orthant in $d$ dimension with random memory.

math.PR↗

arXiv2021

Fluctuations of Transverse Increments in Two-dimensional First Passage Percolation

We consider a model of first passage percolation (FPP) where the nearest-neighbor edges of the standard two-dimensional Euclidean lattice are equipped with random variables. These variables are i.i.d.\, nonnegative, continuous, and have a finite moment generating function in a neighborhood of $0$. We derive consequences about transverse increments of passage times, assuming the model satisfies certain properties. Approximately, the assumed properties are the following: We assume that the standard deviation of the passage time on scale $r$ is of some order $σ(r)$, and $\left\{σ(r), r > 0\right\}$ grows approximately as a power of $r$. Also, the tails of the passage time distributions for distance $r$ satisfy an exponential bound on a scale $σ(r)$ uniformly over $r$. In addition, the boundary of the limit shape in a neighborhood of some fixed direction $θ$ has a uniform quadratic curvature. By transverse increment we mean the difference of passage times from the origin to a pair of points which are located as follows: they are approximately in the same direction, say $θ$, from the origin; the direction of one of them from the other is the direction of the tangent of the boundary of the limit shape at the point on the limit shape in the direction $θ$. The main consequence derived is the following. If $σ(r)$ varies as $r^χ$ for some $χ>0$, and $ξ$ is such that $χ=2ξ-1$, then the fluctuation of the transverse increment of passage time between a pair of points situated at distance $r$ from each other is of the order of $r^{χ/ξ}$.

math.PR↗

arXiv2019

Sparse Minimax Optimality of Bayes Predictive Density Estimates from Clustered Discrete Priors

We consider the problem of predictive density estimation under Kullback-Leibler loss in a high-dimensional Gaussian model with exact sparsity constraints on the location parameters. We study the first order asymptotic minimax risk of Bayes predictive density estimates based on product discrete priors where the proportion of non-zero coordinates converges to zero as dimension increases. Discrete priors that are product of clustered univariate priors provide a tractable configuration for diversification of the future risk and are used for constructing efficient predictive density estimates. We establish that the Bayes predictive density estimate from an appropriately designed clustered discrete prior is asymptotically minimax optimal. The marginals of our proposed prior have infinite clusters of identical sizes. The within cluster support points are equi-probable and the clusters are periodically spaced with geometrically decaying probabilities as they move away from the origin. The cluster periodicity depends on the decay rate of the cluster probabilities. Under different sparsity regimes, through numerical experiments, we compare the maximal risk of the Bayes predictive density estimates from the clustered prior with varied competing estimators including those based on geometrically decaying non-clustered priors of Johnstone (1994) and Mukherjee & Johnstone (2017) and obtain encouraging results.

math.ST↗

arXiv2018

Stochastic Approximation with Random Step Sizes and Urn Models with Random Replacement Matrices Having Finite Mean

Stochastic approximation algorithm is a useful technique which has been exploited successfully in probability theory and statistics for a long time. The step sizes used in stochastic approximation are generally taken to be deterministic and same is true for the drift. However, the specific application of urn models with random replacement matrices motivates us to consider stochastic approximation in a setup where both the step sizes and the drift are random, but the sequence is uniformly bounded. The problem becomes interesting when the negligibility conditions on the errors hold only in probability. We first prove a result on stochastic approximation in this setup, which is new in the literature. Then, as an application, we study urn models with random replacement matrices. In the urn model, the replacement matrices need neither be independent, nor identically distributed. We assume that the replacement matrices are only independent of the color drawn in the same round conditioned on the entire past. We relax the usual second moment assumption on the replacement matrices in the literature and require only first moment to be finite. We require the conditional expectation of the replacement matrix given the past to be close to an irreducible matrix, in an appropriate sense. We do not require any of the matrices to be balanced or nonrandom. We prove convergence of the proportion vector, the composition vector and the count vector in $L^1$, and hence in probability. It is to be noted that the related differential equation is of Lotka-Volterra type and can be analyzed directly.

math.PR↗