arXiv subjects

Guillaume Lecué

Publications and source records attributed to Guillaume Lecué.

At least 19 recordsLinked to original sources

arXiv2026

The Geometry of Statistical Feature Learning in Mean-Field Langevin Dynamics

We introduce a geometric formulation of statistical feature learning for supervised regression. Feature learning is defined through a base--fiber decomposition: the base is the feature-side geometry produced by training, and the fiber is the learned feature space where estimation is performed. We prove this property for spherical mean-field Langevin dynamics, viewed as the Wasserstein gradient flow of a negative entropy-regularized empirical risk. In Gaussian multi-index models, the low-temperature stationary distribution concentrates near the hidden indices, forms a multi-spike structure, and yields parameter recovery with high probability, even though negative entropy regularization penalizes concentration. This concentration has a sharp transition at temperature $λ\asymp 1$. In Gaussian single-index models, the stationary measure satisfies a concentration property, with parity determining whether it lives on $S_2^{d-1}$ or $\mathbb{RP}^{d-1}$. The induced learned feature space aligns the regression signal and yields rates $d/N$ and $Md/N$, up to logarithmic factors.

math.ST↗

arXiv2026

Statistical Inference in Large Multi-way Networks

We propose the Polyads estimator, a new method to estimate structural parameters in weighted multi-way networks while controlling for rich, arbitrary structures of fixed effects. The method is based on a series of classification tasks and is agnostic to both the number and structure of fixed effects. Unlike full maximum likelihood, our estimator does not suffer from the incidental parameter problem: it is consistent and satisfies a Central Limit Theorem with no asymptotic bias, even when some dimensions of the network are short. For sparsely connected networks, it is also computationally faster than PPML. We provide experimental evidence that our estimator yields more reliable confidence intervals, i.e., better empirical coverage, than PPML and its bias-correction strategies. These improvements hold even under model misspecification and are more pronounced in sparse settings. While PPML remains competitive in dense, low-dimensional data, our approach offers a robust alternative for multi-way models that scales efficiently with sparsity. We apply the method to French health insurance claims data to study how a 2017 physician fee reform affected the geography and gender composition of doctor-patient connections.

econ.EM↗

arXiv2026

Sharp convergence rates for Spectral methods via the feature space decomposition method

In this paper, we apply the Feature Space Decomposition (FSD) method developed in [LS24, GLS25, LSSW26, ALSS26] to obtain, under fairly general conditions, matching upper and lower bounds for the population excess risk of spectral methods in linear regression under the squared loss, for every covariance and every signal. This result enables us, for a given linear regression problem, to define a pre-order on the set of spectral methods according to their convergence rates, thereby characterizing which spectral algorithm is superior for that specific problem. Furthermore, this allows us to generalize the saturation effect proposed in inverse problems and to provide necessary and sufficient conditions for its occurrence. Our method also shows that, under broad conditions, any spectral algorithm cannot overcome the barrier of the information exponent in problems such as single-index learning.

math.ST↗

arXiv2024

A Geometrical Analysis of Kernel Ridge Regression and its Applications

We obtain upper bounds for the estimation error of Kernel Ridge Regression (KRR) for all non-negative regularization parameters, offering a geometric perspective on various phenomena in KRR. As applications: 1. We address the multiple descent problem, unifying the proofs of arxiv:1908.10292 and arxiv:1904.12191 for polynomial kernels and we establish multiple descent for the upper bound of estimation error of KRR under sub-Gaussian design and non-asymptotic regimes. 2. For a sub-Gaussian design vector and for non-asymptotic scenario, we prove a one-sided isomorphic version of the Gaussian Equivalent Conjecture. 3. We offer a novel perspective on the linearization of kernel matrices of non-linear kernel, extending it to the power regime for polynomial kernels. 4. Our theory is applicable to data-dependent kernels, providing a convenient and accurate tool for the feature learning regime in deep learning theory. 5. Our theory extends the results in arxiv:2009.14286 under weak moment assumption. Our proof is based on three mathematical tools developed in this paper that can be of independent interest: 1. Dvoretzky-Milman theorem for ellipsoids under (very) weak moment assumptions. 2. Restricted Isomorphic Property in Reproducing Kernel Hilbert Spaces with embedding index conditions. 3. A concentration inequality for finite-degree polynomial kernel functions.

math.ST↗

arXiv2023

Learning with a linear loss function. Excess risk and estimation bounds for ERM, minmax MOM and their regularized versions. Applications to robustness in sparse PCA

Motivated by several examples, we consider a general framework of learning with linear loss functions. In this context, we provide excess risk and estimation bounds that hold with large probability for four estimators: ERM, minmax MOM and their regularized versions. These general bounds are applied for the problem of robustness in sparse PCA. In particular, we improve the state of the art result for this this problems, obtain results under weak moment assumptions as well as for adversarial contaminated data.

math.ST↗

arXiv2023

A geometrical viewpoint on the benign overfitting property of the minimum $l_2$-norm interpolant estimator and its universality

In the linear regression model, the minimum l2-norm interpolant estimator has received much attention since it was proved to be consistent even though it fits noisy data perfectly under some condition on the covariance matrix $Σ$ of the input vector, known as benign overfitting. Motivated by this phenomenon, we study the generalization property of this estimator from a geometrical viewpoint. Our main results extend and improve the convergence rates as well as the deviation probability from [Tsigler and Bartlett]. Our proof differs from the classical bias/variance analysis and is based on the self-induced regularization property introduced in [Bartlett, Montanari and Rakhlin]: the minimum l2-norm interpolant estimator can be written as a sum of a ridge estimator and an overfitting component. The two geometrical properties of random Gaussian matrices at the heart of our analysis are the Dvoretsky-Milman theorem and isomorphic and restricted isomorphic properties. In particular, the Dvoretsky dimension appearing naturally in our geometrical viewpoint, coincides with the effective rank and is the key tool for handling the behavior of the design matrix restricted to the sub-space where overfitting happens. We extend these results to heavy-tailed scenarii proving the universality of this phenomenon beyond exponential moment assumptions. This phenomenon is unknown before and is widely believed to be a significant challenge. This follows from an anistropic version of the probabilistic Dvoretsky-Milman theorem that holds for heavy-tailed vectors which is of independent interest.

math.ST↗

arXiv2021

Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms

We consider the problem of robust mean and location estimation w.r.t. any pseudo-norm of the form $x\in\mathbb{R}^d\to ||x||_S = \sup_{v\in S} $ where $S$ is any symmetric subset of $\mathbb{R}^d$. We show that the deviation-optimal minimax subgaussian rate for confidence $1-δ$ is $$ \max\left(\frac{l^*(Σ^{1/2}S)}{\sqrt{N}}, \sup_{v\in S}||Σ^{1/2}v||_2\sqrt{\frac{\log(1/δ)}{N}}\right) $$where $l^*(Σ^{1/2}S)$ is the Gaussian mean width of $Σ^{1/2}S$ and $Σ$ the covariance of the data (in the benchmark i.i.d. Gaussian case). This improves the entropic minimax lower bound from [Lugosi and Mendelson, 2019] and closes the gap characterized by Sudakov's inequality between the entropy and the Gaussian mean width for this problem. This shows that the right statistical complexity measure for the mean estimation problem is the Gaussian mean width. We also show that this rate can be achieved by a solution to a convex optimization problem in the adversarial and $L_2$ heavy-tailed setup by considering minimum of some Fenchel-Legendre transforms constructed using the Median-of-means principle. We finally show that this rate may also be achieved in situations where there is not even a first moment but a location parameter exists.

math.ST↗

arXiv2021

On the robustness to adversarial corruption and to heavy-tailed data of the Stahel-Donoho median of means

We consider median of means (MOM) versions of the Stahel-Donoho outlyingness (SDO) [stahel 1981, donoho 1982] and of Median Absolute Deviation (MAD) functions to construct subgaussian estimators of a mean vector under adversarial contamination and heavy-tailed data. We develop a single analysis of the MOM version of the SDO which covers all cases ranging from the Gaussian case to the L2 case. It is based on isomorphic and almost isometric properties of the MOM versions of SDO and MAD. This analysis also covers cases where the mean does not even exist but a location parameter does; in those cases we still recover the same subgaussian rates and the same price for adversarial contamination even though there is not even a first moment. These properties are achieved by the classical SDO median and are therefore the first non-asymptotic statistical bounds on the Stahel-Donoho median complementing the $\sqrt{n}$-consistency [maronna 1995] and asymptotic normality [Zuo, Cui, He, 2004] of the Stahel-Donoho estimators. We also show that the MOM version of MAD can be used to construct an estimator of the covariance matrix under only a L2-moment assumption or of a scale parameter if a second moment does not exist.

math.ST↗

arXiv2021

Robust high dimensional learning for Lipschitz and convex losses

We establish risk bounds for Regularized Empirical Risk Minimizers (RERM) when the loss is Lipschitz and convex and the regularization function is a norm. In a first part, we obtain these results in the i.i.d. setup under subgaussian assumptions on the design. In a second part, a more general framework where the design might have heavier tails and data may be corrupted by outliers both in the design and the response variables is considered. In this situation, RERM performs poorly in general. We analyse an alternative procedure based on median-of-means principles and called minmax MOM. We show optimal subgaussian deviation rates for these estimators in the relaxed setting. The main results are meta-theorems allowing a wide-range of applications to various problems in learning theory. To show a non-exhaustive sample of these potential applications, it is applied to classification problems with logistic loss functions regularized by LASSO and SLOPE, to regression problems with Huber loss regularized by Group LASSO and Total Variation. Another advantage of the minmax MOM formulation is that it suggests a systematic way to slightly modify descent based algorithms used in high-dimensional statistics to make them robust to outliers. We illustrate this principle in a Simulations section where a minmax MOM version of classical proximal descent algorithms are turned into robust to outliers algorithms.

math.ST↗

arXiv2020

Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature

Many statistical learning problems have recently been shown to be amenable to Semi-Definite Programming (SDP), with community detection and clustering in Gaussian mixture models as the most striking instances [javanmard et al., 2016]. Given the growing range of applications of SDP-based techniques to machine learning problems, and the rapid progress in the design of efficient algorithms for solving SDPs, an intriguing question is to understand how the recent advances from empirical process theory can be put to work in order to provide a precise statistical analysis of SDP estimators. In the present paper, we borrow cutting edge techniques and concepts from the learning theory literature, such as fixed point equations and excess risk curvature arguments, which yield general estimation and prediction results for a wide class of SDP estimators. From this perspective, we revisit some classical results in community detection from [guédon et al.,2016] and [chen et al., 2016], and we obtain statistical guarantees for SDP estimators used in signed clustering, group synchronization and MAXCUT.

math.ST↗

arXiv2019

Robust subgaussian estimation of a mean vector in nearly linear time

We construct an algorithm, running in time $\tilde{\mathcal O}(N d + uK d)$, which is robust to outliers and heavy-tailed data and which achieves the subgaussian rate from [Lugosi, Mendelson] \begin{equation}\label{eq:intro_subgaus_rate} \sqrt{\frac{{\rm Tr}(Σ)}{N}}+\sqrt{\frac{||Σ||_{op}K}{N}} \end{equation}with probability at least $1-\exp(-c_0K)-\exp(-c_1 u)$ where $Σ$ is the covariance matrix of the informative data, $K\in\{1, \ldots, K\}$ is some parameter (number of block means) and $u>0$ is another parameter of the algorithm. This rate is achieved when $K\geq c_1 |\mathcal O|$ where $|\mathcal O|$ is the number of outliers in the database and under the only assumption that the informative data have a second moment. The algorithm is fully data-dependent and does not use in its construction the proportion of outliers nor the rate above. Its construction combines recently developed tools for Median-of-Means estimators and covering-Semi-definite Programming [Chen, Diakonikolas, Ge] and [Peng, Tangwongsan, Zhang].

math.ST↗

arXiv2019

A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning

Hyperparameters tuning and model selection are important steps in machine learning. Unfortunately, classical hyperparameter calibration and model selection procedures are sensitive to outliers and heavy-tailed data. In this work, we construct a selection procedure which can be seen as a robust alternative to cross-validation and is based on a median-of-means principle. Using this procedure, we also build an ensemble method which, trained with algorithms and corrupted heavy-tailed data, selects an algorithm, trains it with a large uncorrupted subsample and automatically tune its hyperparameters. The construction relies on a divide-and-conquer methodology, making this method easily scalable for autoML given a corrupted database. This method is tested with the LASSO which is known to be highly sensitive to outliers.

math.ST↗

arXiv2018

Robust classification via MOM minimization

We present an extension of Vapnik's classical empirical risk minimizer (ERM) where the empirical risk is replaced by a median-of-means (MOM) estimator, the new estimators are called MOM minimizers. While ERM is sensitive to corruption of the dataset for many classical loss functions used in classification, we show that MOM minimizers behave well in theory, in the sense that it achieves Vapnik's (slow) rates of convergence under weak assumptions: data are only required to have a finite second moment and some outliers may also have corrupted the dataset. We propose an algorithm inspired by MOM minimizers. These algorithms can be analyzed using arguments quite similar to those used for Stochastic Block Gradient descent. As a proof of concept, we show how to modify a proof of consistency for a descent algorithm to prove consistency of its MOM version. As MOM algorithms perform a smart subsampling, our procedure can also help to reduce substantially time computations and memory ressources when applied to non linear algorithms. These empirical performances are illustrated on both simulated and real datasets.

math.ST↗

arXiv2018

Minimax regularization

Classical approach to regularization is to design norms enhancing smoothness or sparsity and then to use this norm or some power of this norm as a regularization function. The choice of the regularization function (for instance a power function) in terms of the norm is mostly dictated by computational purpose rather than theoretical considerations. In this work, we design regularization functions that are motivated by theoretical arguments. To that end we introduce a concept of optimal regularization called "minimax regularization" and, as a proof of concept, we show how to construct such a regularization function for the $\ell_1^d$ norm for the random design setup. We develop a similar construction for the deterministic design setup. It appears that the resulting regularized procedures are different from the one used in the LASSO in both setups.

math.ST↗

arXiv2017

Robust machine learning by median-of-means : theory and practice

We introduce new estimators for robust machine learning based on median-of-means (MOM) estimators of the mean of real valued random variables. These estimators achieve optimal rates of convergence under minimal assumptions on the dataset. The dataset may also have been corrupted by outliers on which no assumption is granted. We also analyze these new estimators with standard tools from robust statistics. In particular, we revisit the concept of breakdown point. We modify the original definition by studying the number of outliers that a dataset can contain without deteriorating the estimation properties of a given estimator. This new notion of breakdown number, that takes into account the statistical performances of the estimators, is non-asymptotic in nature and adapted for machine learning purposes. We proved that the breakdown number of our estimator is of the order of (number of observations)*(rate of convergence). For instance, the breakdown number of our estimators for the problem of estimation of a d-dimensional vector with a noise variance sigma^2 is sigma^2d and it becomes sigma^2 s log(d/s) when this vector has only s non-zero component. Beyond this breakdown point, we proved that the rate of convergence achieved by our estimator is (number of outliers) divided by (number of observation). Besides these theoretical guarantees, the major improvement brought by these new estimators is that they are easily computable in practice. In fact, basically any algorithm used to approximate the standard Empirical Risk Minimizer (or its regularized versions) has a robust version approximating our estimators. As a proof of concept, we study many algorithms for the classical LASSO estimator. A byproduct of the MOM algorithms is a measure of depth of data that can be used to detect outliers.

math.ST↗

arXiv2017

Towards the study of least squares estimators with convex penalty

Penalized least squares estimation is a popular technique in high-dimensional statistics. It includes such methods as the LASSO, the group LASSO, and the nuclear norm penalized least squares. The existing theory of these methods is not fully satisfying since it allows one to prove oracle inequalities with fixed high probability only for the estimators depending on this probability. Furthermore, the control of compatibility factors appearing in the oracle bounds is often not explicit. Some very recent developments suggest that the theory of oracle inequalities can be revised in an improved way. In this paper, we provide an overview of ideas and tools leading to such an improved theory. We show that, along with overcoming the disadvantages mentioned above, the methodology extends to the hilbertian framework and it applies to a large class of convex penalties. This paper is partly expository. In particular, we provide adapted proofs of some results from other recent work.

math.ST↗

arXiv2017

Slope meets Lasso: improved oracle bounds and optimality

We show that two polynomial time methods, a Lasso estimator with adaptively chosen tuning parameter and a Slope estimator, adaptively achieve the exact minimax prediction and $\ell_2$ estimation rate $(s/n)\log (p/s)$ in high-dimensional linear regression on the class of $s$-sparse target vectors in $\mathbb R^p$. This is done under the Restricted Eigenvalue (RE) condition for the Lasso and under a slightly more constraining assumption on the design for the Slope. The main results have the form of sharp oracle inequalities accounting for the model misspecification error. The minimax optimal bounds are also obtained for the $\ell_q$ estimation errors with $1\le q\le 2$ when the model is well-specified. The results are non-asymptotic, and hold both in probability and in expectation. The assumptions that we impose on the design are satisfied with high probability for a large class of random matrices with independent and possibly anisotropically distributed rows. We give a comparative analysis of conditions, under which oracle bounds for the Lasso and Slope estimators can be obtained. In particular, we show that several known conditions, such as the RE condition and the sparse eigenvalue condition are equivalent if the $\ell_2$-norms of regressors are uniformly bounded.

math.ST↗

arXiv2017

Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions

We obtain estimation error rates and sharp oracle inequalities for regularization procedures of the form \begin{equation*} \hat f \in argmin_{f\in F}\left(\frac{1}{N}\sum_{i=1}^N\ell(f(X_i), Y_i)+λ\|f\|\right) \end{equation*} when $\|\cdot\|$ is any norm, $F$ is a convex class of functions and $\ell$ is a Lipschitz loss function satisfying a Bernstein condition over $F$. We explore both the bounded and subgaussian stochastic frameworks for the distribution of the $f(X_i)$'s, with no assumption on the distribution of the $Y_i$'s. The general results rely on two main objects: a complexity function, and a sparsity equation, that depend on the specific setting in hand (loss $\ell$ and norm $\|\cdot\|$). As a proof of concept, we obtain minimax rates of convergence in the following problems: 1) matrix completion with any Lipschitz loss function, including the hinge and logistic loss for the so-called 1-bit matrix completion instance of the problem, and quantile losses for the general case, which enables to estimate any quantile on the entries of the matrix; 2) logistic LASSO and variants such as the logistic SLOPE; 3) kernel methods, where the loss is the hinge loss, and the regularization function is the RKHS norm.

math.ST↗