Searcharxiv⌕ Search

arXiv subjects

Gabor Lugosi

Publications and source records attributed to Gabor Lugosi.

At least 19 recordsLinked to original sources
arXiv2026

A study of centrality measures in random recursive trees

We investigate the behaviour of five classical centrality measures--Jordan, rumor, betweenness, degree, and closeness centralities--in the setting of uniform random recursive trees. Motivated by applications in network archaeology, we focus on two fundamental questions: (i) the birth index (time of arrival) of the most central vertex, and (ii) the relative centrality of the root. We quantify the probability that the root is the most central vertex, analyze its expected rank under each centrality measure, and determine the expected birth index of a central vertex. In addition, we characterize the typical size of the set of top-ranked vertices that contains the root with high probability. Finally, for each centrality notion, we study the persistence properties of the center and the asymptotic behaviour of the root's rank.

math.PR↗
arXiv2025

Convergence of continuous-time stochastic gradient descent with applications to deep neural networks

We study a continuous-time approximation of the stochastic gradient descent process for minimizing the population expected loss in learning problems. The main results establish general sufficient conditions for the convergence, extending the results of Chatterjee (2022) established for (nonstochastic) gradient descent. We show how the main result can be applied to the case of overparametrized neural network training.

cs.LG↗
arXiv2025

Finding a Nash equilibrium of a random win-lose game in expected polynomial time

A long-standing open problem in algorithmic game theory asks whether or not there is a polynomial time algorithm to compute a Nash equilibrium in a random bimatrix game. We study random win-lose games, where the entries of the $n\times n$ payoff matrices are independent and identically distributed (i.i.d.) Bernoulli random variables with parameter $p=p(n)$. We prove that, for nearly all values of the parameter $p=p(n)$, there is an expected polynomial-time algorithm to find a Nash equilibrium in a random win-lose game. More precisely, if $p\sim cn^{-a}$ for some parameters $a,c\ge 0$, then there is an expected polynomial-time algorithm whenever $a\not\in \{1/2, 1\}$. In addition, if $a = 1/2$ there is an efficient algorithm if either $c \le e^{-52} 2^{-8} $ or $c\ge 0.977$. If $a=1$, then there is an expected polynomial-time algorithm if either $c\le 0.3849$ or $c\ge \log^9 n$.

cs.GT↗
arXiv2025

Robust, sub-Gaussian mean estimators in metric spaces

Estimating the mean of a random vector from i.i.d. data has received considerable attention, and the optimal accuracy one may achieve with a given confidence is fairly well understood by now. When the data take values in more general metric spaces, an appropriate extension of the notion of the mean is the Fréchet mean. While asymptotic properties of the most natural Fréchet mean estimator (the empirical Fréchet mean) have been thoroughly researched, non-asymptotic performance bounds have only been studied recently. The aim of this paper is to study the performance of estimators of the Fréchet mean in general metric spaces under possibly heavy-tailed and contaminated data. In such cases, the empirical Fréchet mean is a poor estimator. We propose a general estimator based on high-dimensional extensions of trimmed means and prove general performance bounds. Unlike all previously established bounds, ours generalize the optimal bounds known for Euclidean data. The main message of the bounds is that, much like in the Euclidean case, the optimal accuracy is governed by two "variance" terms: a "global variance" term that is independent of the prescribed confidence, and a potentially much smaller, confidence-dependent "local variance" term. We apply our results for metric spaces with curvature bounded from below, such as Wasserstein spaces, and for uniformly convex Banach spaces.

math.ST↗
arXiv2025

Learning latent tree models with small query complexity

We consider the problem of structure recovery in a graphical model of a tree where some variables are latent. Specifically, we focus on the Gaussian case, which can be reformulated as a well-studied problem: recovering a semi-labeled tree from a distance metric. We introduce randomized procedures that achieve query complexity of optimal order. Additionally, we provide statistical analysis for scenarios where the tree distances are noisy. The Gaussian setting can be extended to other situations, including the binary case and non-paranormal distributions.

math.ST↗
arXiv2025

On the size of temporal cliques in subcritical random temporal graphs

A \emph{random temporal graph} is an Erdős-Rényi random graph $G(n,p)$, together with a random ordering of its edges. A path in the graph is called \emph{increasing} if the edges on the path appear in increasing order. A set $S$ of vertices forms a \emph{temporal clique} if for all $u,v \in S$, there is an increasing path from $u$ to $v$. \cite{Becker2023} proved that if $p=c\log n/n$ for $c>1$, then, with high probability, there is a temporal clique of size $n-o(n)$. On the other hand, for $c<1$, with high probability, the largest temporal clique is of size $o(n)$. In this note we improve the latter bound by showing that, for $c<1$, the largest temporal clique is of \emph{constant} size with high probability.

math.PR↗
arXiv2025

Broadcasting in random recursive dags

A uniform $k$-{\sc dag} generalizes the uniform random recursive tree by picking $k$ parents uniformly at random from the existing nodes. It starts with $k$ ''roots''. Each of the $k$ roots is assigned a bit. These bits are propagated by a noisy channel. The parents' bits are flipped with probability $p$, and a majority vote is taken. When all nodes have received their bits, the $k$-{\sc dag} is shown without identifying the roots. The goal is to estimate the majority bit among the roots. We identify the threshold for $p$ as a function of $k$ below which the majority rule among all nodes yields an error $c+o(1)$ with $c<1/2$. Above the threshold the majority rule errs with probability $1/2+o(1)$.

stat.ML↗
arXiv2025

Uniform temporal trees

Motivated by the study of random temporal networks, we introduce a class of random trees that we coin \emph{uniform temporal trees}. A uniform temporal tree is obtained by assigning independent uniform $[0,1]$ labels to the edges of a rooted complete infinite $n$-ary tree and keeping only those vertices for which the path from the root to the vertex has decreasing edge labels. The $p$-percolated uniform temporal tree, denoted by $\mathcal{T}_{n,p}$, is obtained similarly, with the additional constraint that the edge labels on each path are all below $p$. We study several properties of these trees, including their size, height, the typical depth of a vertex, and degree distribution. In particular, we establish a limit law for the size of $\mathcal{T}_{n,p}$ which states that $\frac{|\mathcal{T}_{n,p}|}{e^{np}}$ converges in distribution to an $\exponential(1)$ random variable as $n \to \infty$. For the height $H_{n,p}$, we prove that $\frac{H_{n,p}}{np}$ converges to $e$ in probability. Uniform temporal trees show some remarkable similarities to uniform random recursive trees.

math.PR↗
arXiv2024

Subtractive random forests

Motivated by online recommendation systems, we study a family of random forests. The vertices of the forest are labeled by integers. Each non-positive integer $i\le 0$ is the root of a tree. Vertices labeled by positive integers $n \ge 1$ are attached sequentially such that the parent of vertex $n$ is $n-Z_n$, where the $Z_n$ are i.i.d.\ random variables taking values in $\mathbb N$. We study several characteristics of the resulting random forest. In particular, we establish bounds for the expected tree sizes, the number of trees in the forest, the number of leaves, the maximum degree, and the height of the forest. We show that for all distributions of the $Z_n$, the forest contains at most one infinite tree, almost surely. If ${\mathbb E} Z_n < \infty$, then there is a unique infinite tree and the total size of the remaining trees is finite, with finite expected value if ${\mathbb E}Z_n^2 < \infty$. If ${\mathbb E} Z_n = \infty$ then almost surely all trees are finite.

math.PR↗
arXiv2024

Facets of high-dimensional Gaussian polytopes

We study the number of facets of the convex hull of n independent standard Gaussian points in d-dimensional Euclidean space. In particular, we are interested in the expected number of facets when the dimension is allowed to grow with the sample size. We establish an explicit asymptotic formula that is valid whenever d/n tends to zero. We also obtain the asymptotic value when d is close to n.

math.PR↗
arXiv2023

A note on estimating the dimension from a random geometric graph

Let $G_n$ be a random geometric graph with vertex set $[n]$ based on $n$ i.i.d.\ random vectors $X_1,\ldots,X_n$ drawn from an unknown density $f$ on $\R^d$. An edge $(i,j)$ is present when $\|X_i -X_j\| \le r_n$, for a given threshold $r_n$ possibly depending upon $n$, where $\| \cdot \|$ denotes Euclidean distance. We study the problem of estimating the dimension $d$ of the underlying space when we have access to the adjacency matrix of the graph but do not know $r_n$ or the vectors $X_i$. The main result of the paper is that there exists an estimator of $d$ that converges to $d$ in probability as $n \to \infty$ for all densities with $\int f^5 < \infty$ whenever $n^{3/2} r_n^d \to \infty$ and $r_n = o(1)$. The conditions allow very sparse graphs since when $n^{3/2} r_n^d \to 0$, the graph contains isolated edges only, with high probability. We also show that, without any condition on the density, a consistent estimator of $d$ exists when $n r_n^d \to \infty$ and $r_n = o(1)$.

stat.ML↗
arXiv2023

Increasing paths in random temporal graphs

We consider random temporal graphs, a version of the classical Erdős--Rényi random graph G(n,p) where additionally, each edge has a distinct random time stamp, and connectivity is constrained to sequences of edges with increasing time stamps. We study the asymptotics for the distances in such graphs, mostly in the regime of interest where np is of order log n. We establish the first order asymptotics for the lengths of increasing paths: the lengths of the shortest and longest paths between typical vertices, the maxima of these lengths from a given vertex, as well as the maxima between any two vertices; this covers the (temporal) diameter.

math.PR↗
arXiv2021

Broadcasting on random recursive trees

We study the broadcasting problem when the underlying tree is a random recursive tree. The root of the tree has a random bit value assigned. Every other vertex has the same bit value as its parent with probability $1-q$ and the opposite value with probability $q$, where $q \in [0,1]$. The broadcasting problem consists in estimating the value of the root bit upon observing the unlabeled tree, together with the bit value associated with every vertex. In a more difficult version of the problem, the unlabeled tree is observed but only the bit values of the leaves are observed. When the underlying tree is a uniform random recursive tree, in both variants of the problem we characterize the values of $q$ for which the optimal reconstruction method has a probability of error bounded away from $1/2$. We also show that the probability of error is bounded by a constant times $q$. Two simple reconstruction rules are analyzed in detail. One of them is the simple majority vote, the other is the bit value of the centroid of the tree. Most results are extended to linear preferential attachment trees as well.

math.PR↗
arXiv2021

Multiplayer bandits without observing collision information

We study multiplayer stochastic multi-armed bandit problems in which the players cannot communicate and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider two feedback models: a model in which the players can observe whether a collision has occurred and a more difficult setup when no collision information is available. We give the first theoretical guarantees for the second model: an algorithm with a logarithmic regret, and an algorithm with a square-root regret type that does not depend on the gaps between the means. For the first model, we give the first square-root regret bounds that do not depend on the gaps. Building on these ideas, we also give an algorithm for reaching approximate Nash equilibria quickly in stochastic anti-coordination games.

cs.LG↗
arXiv2020

On Mean Estimation for Heteroscedastic Random Variables

We study the problem of estimating the common mean $μ$ of $n$ independent symmetric random variables with different and unknown standard deviations $σ_1 \le σ_2 \le \cdots \leσ_n$. We show that, under some mild regularity assumptions on the distribution, there is a fully adaptive estimator $\widehatμ$ such that it is invariant to permutations of the elements of the sample and satisfies that, up to logarithmic factors, with high probability, \[ |\widehatμ - μ| \lesssim \min\left\{σ_{m^*}, \frac{\sqrt{n}}{\sum_{i = \sqrt{n}}^n σ_i^{-1}} \right\}~, \] where the index $m^* \lesssim \sqrt{n}$ satisfies $m^* \approx \sqrt{σ_{m^*}\sum_{i = m^*}^nσ_i^{-1}}$.

math.ST↗
arXiv2020

Multivariate mean estimation with direction-dependent accuracy

We consider the problem of estimating the mean of a random vector based on $N$ independent, identically distributed observations. We prove the existence of an estimator that has a near-optimal error in all directions in which the variance of the one dimensional marginal of the random vector is not too small: with probability $1-δ$, the procedure returns $\whμ_N$ which satisfies that for every direction $u \in S^{d-1}$, \[ \inr{\whμ_N - μ, u}\le \frac{C}{\sqrt{N}} \left( σ(u)\sqrt{\log(1/δ)} + \left(\E\|X-\EXP X\|_2^2\right)^{1/2} \right)~, \] where $σ^2(u) = \var(\inr{X,u})$ and $C$ is a constant. To achieve this, we require only slightly more than the existence of the covariance matrix, in the form of a certain moment-equivalence assumption. The proof relies on novel bounds for the ratio of empirical and true probabilities that hold uniformly over certain classes of random variables.

math.ST↗
arXiv2019

Mean estimation and regression under heavy-tailed distributions--a survey

We survey some of the recent advances in mean estimation and regression function estimation. In particular, we describe sub-Gaussian mean estimators for possibly heavy-tailed data both in the univariate and multivariate settings. We focus on estimators based on median-of-means techniques but other methods such as the trimmed mean and Catoni's estimator are also reviewed. We give detailed proofs for the cornerstone results. We dedicate a section on statistical learning problems--in particular, regression function estimation--in the presence of possibly heavy-tailed data.

math.ST↗