Searcharxiv⌕ Search

arXiv subjects

Alexandre Tsybakov

Publications and source records attributed to Alexandre Tsybakov.

15 recordsLinked to original sources
arXiv2026

Sharp Optimal Algorithm for Derivative-Free Stochastic Convex Optimization in One Dimension

Stochastic convex optimization is a classical problem with well-understood guarantees under first-order feedback. In contrast, for zero-order optimization with noisy function evaluations, a logarithmic gap has persisted between known upper bounds and the $\Omega(1/\sqrt{T})$ lower bound, even in the one-dimensional case. In this work, we study the problem of minimizing a convex function $f : [0,1] \to [0,1]$ using a zero-order oracle with subGaussian noise. We propose a computationally efficient algorithm that achieves the optimal $O(1/\sqrt{T})$ convergence rate, matching the lower bound. The result closes the existing gap in one dimension, providing the first sharp rate guarantee in this setting.

math.OC↗
arXiv2024

Generalized multi-view model: Adaptive density estimation under low-rank constraints

We study the problem of bivariate discrete or continuous probability density estimation under low-rank constraints.For discrete distributions, we assume that the two-dimensional array to estimate is a low-rank probability matrix. In the continuous case, we assume that the density with respect to the Lebesgue measure satisfies a generalized multi-view model, meaning that it is $\beta$-H{\"o}lder and can be decomposed as a sum of $K$ components, each of which is a product of one-dimensional functions. In both settings, we propose estimators that achieve, up to logarithmic factors, the minimax optimal convergence rates under such low-rank constraints. In the discrete case, the proposed estimator is adaptive to the rank $K$. In the continuous case, our estimator converges with the $L_1$ rate $\min((K/n)^{\beta/(2\beta+1)}, n^{-\beta/(2\beta+2)})$ up to logarithmic factors, and it is adaptive to the unknown support as well as to the smoothness $\beta$ and to the unknown number of separable components $K$. We present efficient algorithms for computing our estimators.

math.ST↗
arXiv2021

Assigning Topics to Documents by Successive Projections

Topic models provide a useful tool to organize and understand the structure of large corpora of text documents, in particular, to discover hidden thematic structure. Clustering documents from big unstructured corpora into topics is an important task in various areas, such as image analysis, e-commerce, social networks, population genetics. A common approach to topic modeling is to associate each topic with a probability distribution on the dictionary of words and to consider each document as a mixture of topics. Since the number of topics is typically substantially smaller than the size of the corpus and of the dictionary, the methods of topic modeling can lead to a dramatic dimension reduction. In this paper, we study the problem of estimating topics distribution for each document in the given corpus, that is, we focus on the clustering aspect of the problem. We introduce an algorithm that we call Successive Projection Overlapping Clustering (SPOC) inspired by the Successive Projection Algorithm for separable matrix factorization. This algorithm is simple to implement and computationally fast. We establish theoretical guarantees on the performance of the SPOC algorithm, in particular, near matching minimax upper and lower bounds on its estimation risk. We also propose a new method that estimates the number of topics. We complement our theoretical results with a numerical study on synthetic and semi-synthetic data to analyze the performance of this new algorithm in practice. One of the conclusions is that the error of the algorithm grows at most logarithmically with the size of the dictionary, in contrast to what one observes for Latent Dirichlet Allocation.

math.ST↗
arXiv2019

Algorithms of Robust Stochastic Optimization Based on Mirror Descent Method

We propose an approach to construction of robust non-Euclidean iterative algorithms for convex composite stochastic optimization based on truncation of stochastic gradients. For such algorithms, we establish sub-Gaussian confidence bounds under weak assumptions about the tails of the noise distribution in convex and strongly convex settings. Robust estimates of the accuracy of general stochastic algorithms are also proposed.

math.ST↗
arXiv2014

Linear and Conic Programming Estimators in High-Dimensional Errors-in-variables Models

We consider the linear regression model with observation error in the design. In this setting, we allow the number of covariates to be much larger than the sample size. Several new estimation methods have been recently introduced for this model. Indeed, the standard Lasso estimator or Dantzig selector turn out to become unreliable when only noisy regressors are available, which is quite common in practice. We show in this work that under suitable sparsity assumptions, the procedure introduced in Rosenbaum and Tsybakov (2013) is almost optimal in a minimax sense and, despite non-convexities, can be efficiently computed by a single linear programming problem. Furthermore, we provide an estimator attaining the minimax efficiency bound. This estimator is written as a second order cone programming minimisation problem which can be solved numerically in polynomial time.

math.ST↗
arXiv2013

Pivotal estimation in high-dimensional regression via linear programming

We propose a new method of estimation in high-dimensional linear regression model. It allows for very weak distributional assumptions including heteroscedasticity, and does not require the knowledge of the variance of random errors. The method is based on linear programming only, so that its numerical implementation is faster than for previously known techniques using conic programs, and it allows one to deal with higher dimensional models. We provide upper bounds for estimation and prediction errors of the proposed estimator showing that it achieves the same rate as in the more restrictive situation of fixed design and i.i.d. Gaussian errors with known variance. Following Gautier and Tsybakov (2011), we obtain the results under weaker sensitivity assumptions than the restricted eigenvalue or assimilated conditions.

math.ST↗
arXiv2013

Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity

We study the problem of aggregation under the squared loss in the model of regression with deterministic design. We obtain sharp PAC-Bayesian risk bounds for aggregates defined via exponential weights, under general assumptions on the distribution of errors and on the functions to aggregate. We then apply these results to derive sparsity oracle inequalities.

math.ST↗
arXiv2013

Statistical inference in compound functional models

We consider a general nonparametric regression model called the compound model. It includes, as special cases, sparse additive regression and nonparametric (or linear) regression with many covariates but possibly a small number of relevant covariates. The compound model is characterized by three main parameters: the structure parameter describing the "macroscopic" form of the compound function, the "microscopic" sparsity parameter indicating the maximal number of relevant covariates in each component and the usual smoothness parameter corresponding to the complexity of the members of the compound. We find non-asymptotic minimax rate of convergence of estimators in such a model as a function of these three parameters. We also show that this rate can be attained in an adaptive way.

math.ST↗
arXiv2010

Exponential Screening and optimal rates of sparse estimation

In high-dimensional linear regression, the goal pursued here is to estimate an unknown regression function using linear combinations of a suitable set of covariates. One of the key assumptions for the success of any statistical procedure in this setup is to assume that the linear combination is sparse in some sense, for example, that it involves only few covariates. We consider a general, non necessarily linear, regression with Gaussian noise and study a related question that is to find a linear combination of approximating functions, which is at the same time sparse and has small mean squared error (MSE). We introduce a new estimation procedure, called Exponential Screening that shows remarkable adaptation properties. It adapts to the linear combination that optimally balances MSE and sparsity, whether the latter is measured in terms of the number of non-zero entries in the combination ($\ell_0$ norm) or in terms of the global weight of the combination ($\ell_1$ norm). The power of this adaptation result is illustrated by showing that Exponential Screening solves optimally and simultaneously all the problems of aggregation in Gaussian regression that have been discussed in the literature. Moreover, we show that the performance of the Exponential Screening estimator cannot be improved in a minimax sense, even if the optimal sparsity is known in advance. The theoretical and numerical superiority of Exponential Screening compared to state-of-the-art sparse procedures is also discussed.

math.ST↗
arXiv2007

Sparsity oracle inequalities for the Lasso

This paper studies oracle properties of $\ell_1$-penalized least squares in nonparametric regression setting with random design. We show that the penalized least squares estimator satisfies sparsity oracle inequalities, i.e., bounds in terms of the number of non-zero components of the oracle vector. The results are valid even when the dimension of the model is (much) larger than the sample size and the regression matrix is not positive definite. They can be applied to high-dimensional linear regression, to nonparametric adaptive regression estimation and to the problem of aggregation of arbitrary estimators.

math.ST↗
arXiv2006

Linear and convex aggregation of density estimators

We study the problem of linear and convex aggregation of $M$ estimators of a density with respect to the mean squared risk. We provide procedures for linear and convex aggregation and we prove oracle inequalities for their risks. We also obtain lower bounds showing that these procedures are rate optimal in a minimax sense. As an example, we apply general results to aggregation of multivariate kernel density estimators with different bandwidths. We show that linear and convex aggregates mimic the kernel oracles in asymptotically exact sense for a large class of kernels including Gaussian, Silverman's and Pinsker's ones. We prove that, for Pinsker's kernel, the proposed aggregates are sharp asymptotically minimax simultaneously over a large scale of Sobolev classes of densities. Finally, we provide simulations demonstrating performance of the convex aggregation procedure.

math.ST↗
arXiv2006

Recursive Aggregation of Estimators by Mirror Descent Algorithm with Averaging

We consider a recursive algorithm to construct an aggregated estimator from a finite number of base decision rules in the classification problem. The estimator approximately minimizes a convex risk functional under the l1-constraint. It is defined by a stochastic version of the mirror descent algorithm (i.e., of the method which performs gradient descent in the dual space) with an additional averaging. The main result of the paper is an upper bound for the expected accuracy of the proposed estimator. This bound is of the order $\sqrt{(\log M)/t}$ with an explicit and small constant factor, where $M$ is the dimension of the problem and $t$ stands for the sample size. A similar bound is proved for a more general setting that covers, in particular, the regression model with squared loss.

math.ST↗
arXiv2004

Aggregation for Regression Learning

This paper studies statistical aggregation procedures in regression setting. A motivating factor is the existence of many different methods of estimation, leading to possibly competing estimators. We consider here three different types of aggregation: model selection (MS) aggregation, convex (C) aggregation and linear (L) aggregation. The objective of (MS) is to select the optimal single estimator from the list; that of (C) is to select the optimal convex combination of the given estimators; and that of (L) is to select the optimal linear combination of the given estimators. We are interested in evaluating the rates of convergence of the excess risks of the estimators obtained by these procedures. Our approach is motivated by recent minimax results in Nemirovski (2000) and Tsybakov (2003). There exist competing aggregation procedures achieving optimal convergence separately for each one of (MS), (C) and (L) cases. Since the bounds in these results are not directly comparable with each other, we suggest an alternative solution. We prove that all the three optimal bounds can be nearly achieved via a single "universal" aggregation procedure. We propose such a procedure which consists in mixing of the initial estimators with the weights obtained by penalized least squares. Two different penalities are considered: one of them is related to hard thresholding techniques, the second one is a data dependent $L_1$-type penalty. Consequently, our method can be endorsed by both the proponents of model selection and the advocates of model averaging.

math.ST↗