Zobrazeno 1 - 10
of 101
pro vyhledávání: '"Dalalyan, A. S."'
Autor:
Donier-Meroz, Etienne, Dalalyan, Arnak S., Kramarz, Francis, Choné, Philippe, D'Haultfoeuille, Xavier
Many real-world data sets can be presented in the form of a matrix whose entries correspond to the interaction between two entities of different natures (number of times a web user visits a web page, a student's grade in a subject, a patient's rating
Externí odkaz:
http://arxiv.org/abs/2304.03590
Autor:
Dalalyan, Arnak S.
In this note, we consider the problem of aggregation of estimators in order to denoise a signal. The main contribution is a short proof of the fact that the exponentially weighted aggregate satisfies a sharp oracle inequality. While this result was a
Externí odkaz:
http://arxiv.org/abs/2212.12950
We study the problem of robust estimation of the mean vector of a sub-Gaussian distribution. We introduce an estimator based on spectral dimension reduction (SDR) and establish a finite sample upper bound on its error that is minimax-optimal up to a
Externí odkaz:
http://arxiv.org/abs/2204.02323
Autor:
Tinsi, Laura, Dalalyan, Arnak S.
Analysing statistical properties of neural networks is a central topic in statistics and machine learning. However, most results in the literature focus on the properties of the neural network minimizing the training error. The goal of this paper is
Externí odkaz:
http://arxiv.org/abs/2112.11086
Autor:
Karagulyan, Avetik, Dalalyan, Arnak S.
We study the problem of sampling from a probability distribution on $\mathbb R^p$ defined via a convex and smooth potential function. We consider a continuous-time diffusion-type process, termed Penalized Langevin dynamics (PLD), the drift of which i
Externí odkaz:
http://arxiv.org/abs/2006.13998
Autor:
Dalalyan, Arnak S., Minasyan, Arshak
Publikováno v:
Ann. Statist. 50(2): 1193-1219 (April 2022)
The goal of this paper is to show that a single robust estimator of the mean of a multivariate Gaussian distribution can enjoy five desirable properties. First, it is computationally tractable in the sense that it can be computed in a time which is a
Externí odkaz:
http://arxiv.org/abs/2002.01432
In this paper, we provide non-asymptotic upper bounds on the error of sampling from a target density using three schemes of discretized Langevin diffusions. The first scheme is the Langevin Monte Carlo (LMC) algorithm, the Euler discretization of the
Externí odkaz:
http://arxiv.org/abs/1906.08530
Autor:
Dalalyan, Arnak S., Thompson, Philip
We study the problem of estimating a $p$-dimensional $s$-sparse vector in a linear model with Gaussian design and additive noise. In the case where the labels are contaminated by at most $o$ adversarial outliers, we prove that the $\ell_1$-penalized
Externí odkaz:
http://arxiv.org/abs/1904.06288
M-estimators are ubiquitous in machine learning and statistical learning theory. They are used both for defining prediction strategies and for evaluating their precision. In this paper, we propose the first non-asymptotic "any-time" deviation bounds
Externí odkaz:
http://arxiv.org/abs/1903.06576
We consider the problem of estimating the mean of a distribution supported by the $k$-dimensional probability simplex in the setting where an $\varepsilon$ fraction of observations are subject to adversarial corruption. A simple particular example is
Externí odkaz:
http://arxiv.org/abs/1902.04650