Mathématiques, Informatique et Statistique pour l'Environnement et l'Agronomie

Predictions from statistical physics postulate that recovery of the communities in Stochastic Block Model (SBM) is possible in polynomial time above, and only above, the Kesten-Stigum (KS) threshold. This conjecture has given rise to a rich literature, proving that non-trivial community recovery is indeed possible in SBM above the KS threshold, as long as the number $K$ of communities remains smaller than $\sqrt{n}$, where $n$ is the number of nodes in the observed graph. Failure of low-degree polynomials below the KS threshold was also proven when $K=o(\sqrt{n})$. When $K\geq \sqrt{n}$, Chin et al.(2025) recently prove that, in a sparse regime, community recovery in polynomial time is possible below the KS threshold by counting non-backtracking paths. This breakthrough result lead them to postulate a new threshold for the many communities regime $K\geq \sqrt{n}$. In this work, we provide evidences that confirm their conjecture for $K\geq \sqrt{n}$: 1- We prove that, for any density of the graph, low-degree polynomials fail to recover communities below the threshold postulated by Chin et al.(2025); 2- We prove that community recovery is possible in polynomial time above the postulated threshold, not only in the sparse regime of~Chin et al., but also in some (but not all) moderately sparse regimes by essentially by counting occurrences of cliques or self-avoiding paths of suitable size in the observed graph. In addition, we propose a detailed conjecture regarding the structure of motifs that are optimal in sparsity regimes not covered by cliques or self-avoiding paths counting. In particular, counting self-avoiding paths of length $\log(n)$--which is closely related to spectral algorithms based on the Non-Backtracking operator--is optimal only in the sparse regime. Other motif counts--unrelated to spectral properties--should be considered in denser regimes.

Low-degree polynomials have emerged as a powerful paradigm for providing evidence of statistical-computational gaps across a variety of high-dimensional statistical models [Wein25]. For detection problems -- where the goal is to test a planted distribution $\mathbb{P}'$ against a null distribution $\mathbb{P}$ with independent components -- the standard approach is to bound the advantage using an $\mathbb{L}^2(\mathbb{P})$-orthonormal family of polynomials. However, this method breaks down for estimation tasks or more complex testing problems where $\mathbb{P}$ has some planted structures, so that no simple $\mathbb{L}^2(\mathbb{P})$-orthogonal polynomial family is available. To address this challenge, several technical workarounds have been proposed [SW22,SW25], though their implementation can be delicate. In this work, we propose a more direct proof strategy. Focusing on random graph models, we construct a basis of polynomials that is almost orthonormal under $\mathbb{P}$, in precisely those regimes where statistical-computational gaps arise. This almost orthonormal basis not only yields a direct route to establishing low-degree lower bounds, but also allows us to explicitly identify the polynomials that optimize the low-degree criterion. This, in turn, provides insights into the design of optimal polynomial-time algorithms. We illustrate the effectiveness of our approach by recovering known low-degree lower bounds, and establishing new ones for problems such as hidden subcliques, stochastic block models, and seriation models.

The creation of disease-resistant varieties adapted to climate change is a key challenge for the future of the wine industry. At present, the selection of these new varieties is essentially based on screening for genetic markers of resistance and agronomic criteria, due to the small number of vines available per genotype. Integrating screening for oenological criteria into the early stages of selection would speed up this process.

The development of sensors is opening new avenues in several fields of activity. Concerning agricultural crops, complex combinations of agri-environmental dynamics, such as soil and climate variables, are now commonly recorded. These new kinds of measurements are an opportunity to improve knowledge of the drivers of crop yield and crop quality at harvest. This involves renewing statistical approaches to account for the combined variations of these dynamic variables, here considered as temporal variables. The objective of the paper is to estimate an interpretable model to study the influence of the two combined inputs on a scalar output. A Sparse and Structured Procedure is proposed to Identify Combined Effects of Formatted temporal Predictors, hereafter denoted S piceFP. The method is based on the transformation of both temporal variables into categorical variables by defining joint modalities, from which a collection of multiple regression models is then derived. The regressors are the frequencies associated with joint class intervals. The class intervals and related regression coefficients are determined using a generalized fused lasso. S piceFP is a generic and exploratory approach. The simulations we performed show that it is flexible enough to select the non-null or influential modalities of values. A motivating example for grape quality is presented.

This paper introduces a novel approach for epidemic nowcasting and forecasting over networks using total variation (TV) denoising, a method inspired by classical signal processing techniques. Considering a network that models a population as a set of $n$ nodes characterized by their infection statuses $Y_i$ and that represents contacts as edges, we prove the consistency of graph-TV denoising for estimating the underlying infection probabilities $\{p_i\}_{ i \in \{1,\cdots, n\}}$ in the presence of Bernoulli noise. Our results provide an important extension of existing bounds derived in the Gaussian case to the study of binary variables -- an approach hereafter referred to as one-bit total variation denoising. The methodology is further extended to handle incomplete observations, thereby expanding its relevance to various real-world situations where observations over the full graph may not be accessible. Focusing on the context of epidemics, we establish that one-bit total variation denoising enhances both nowcasting and forecasting accuracy in networks, as further evidenced by comprehensive numerical experiments and two real-world examples. The contributions of this paper lie in its theoretical developments, particularly in addressing the incomplete data case, thereby paving the way for more precise epidemic modelling and enhanced surveillance strategies in practical settings.