Alexandre TSYBAKOV


Alexandre TSYBAKOV
CREST Permanent Member
Full Professor
Statistics
Personal Website
This user account status is Approved

Contact

Minimax estimation of functionals in sparse vector model with correlated observations

We consider the observations of an unknown s-sparse vector θ corrupted by Gaussian noise with zero mean and unknown covariance matrix Σ. We propose minimax optimal methods of estimating the ℓ2 n ...

Wang Yuhao, Yang Pengkun, Tsybakov Alexandre

Arxiv, Cornell University, 2024

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 ...

Chhor Julien, Klopp Olga, Tsybakov Alexandre

Arxiv, Cornell University, 2024

Benign overfitting and adaptive nonparametric regression

...

Chhor J,Sigalla S,Tsybakov AB

arXiv [math.ST], 2022

Estimation of the l_2-norm and testing in sparse linear regression with unknown variance

...

Carpentier A,Collier O,Comminges L,Tsybakov AB,Wang Y

Bernoulli, 2022

Estimating the minimizer and the minimum value of a regression function under passive design

...

Akhavan A,Gogolashvili D,Tsybakov AB

arXiv [math.ST], 2022

Improved Clustering Algorithms for the Bipartite Stochastic Block Model

...

Ndaoud M,Sigalla S,Tsybakov AB

IEEE Transactions on Information Theory, 2022

Adaptive robust estimation in sparse vector model

...

Comminges L,Collier O,Ndaoud M,Tsybakov AB

The Annals of Statistics, 2021

Assigning Topics to Documents by Successive Projections

...

Klopp O,Panov M,Sigalla S,Tsybakov AB

Assigning Topics to Documents by Successive Projections. 2021, 2021

On estimation of nonsmooth functionals of sparse normal means

...

Collier O,Comminges L,Tsybakov AB

Bernoulli, 2020

Optimal variable selection and adaptive noisy compressed sensing

...

Ndaoud M,Tsybakov AB

IEEE Transactions on Information Theory, 2020

1 2 >