Zobrazeno 1 - 10
of 94
pro vyhledávání: '"Alexandre B. Tsybakov"'
Publikováno v:
Oberwolfach Reports. 19:1377-1430
In the pivotal variable selection problem, we derive the exact non-asymptotic minimax selector over the class of all $s$-sparse vectors, which is also the Bayes selector with respect to the uniform prior. While this optimal selector is, in general, n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d263334b6bea6e277f02454280eb4cc0
http://arxiv.org/abs/2112.15042
http://arxiv.org/abs/2112.15042
Publikováno v:
Automation and Remote Control / Avtomatika i Telemekhanika
Automation and Remote Control / Avtomatika i Telemekhanika, 2019, 80 (9), pp.1607-1627. ⟨10.1134/S0005117919090042⟩
Automation and Remote Control / Avtomatika i Telemekhanika, MAIK Nauka/Interperiodica, 2019, 80 (9), pp.1607-1627. ⟨10.1134/S0005117919090042⟩
Automation and Remote Control / Avtomatika i Telemekhanika, 2019, 80 (9), pp.1607-1627. ⟨10.1134/S0005117919090042⟩
Automation and Remote Control / Avtomatika i Telemekhanika, MAIK Nauka/Interperiodica, 2019, 80 (9), pp.1607-1627. ⟨10.1134/S0005117919090042⟩
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
Publikováno v:
Bernoulli 25, no. 4B (2019), 3883-3911
We study the problem of matrix estimation and matrix completion under a general framework. This framework includes several important models as special cases such as the Gaussian mixture model, mixed membership model, bi-clustering model and dictionar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::798fe1f3e4ea46d22899410e50656239
https://projecteuclid.org/euclid.bj/1569398788
https://projecteuclid.org/euclid.bj/1569398788
Publikováno v:
Annals of Statistics
Annals of Statistics, In press
Annals of Statistics, Institute of Mathematical Statistics, In press
Annals of Statistics, In press
Annals of Statistics, Institute of Mathematical Statistics, In press
International audience; For the sparse vector model, we consider estimation of the target vector, of its l2-norm and of the noise variance. We construct adaptive estimators and establish the optimal rates of adaptive estimation when adaptation is con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db3f298dc30ddee5611a1baf8efd9acc
https://hal.archives-ouvertes.fr/hal-01707612v2/document
https://hal.archives-ouvertes.fr/hal-01707612v2/document
Publikováno v:
Bernoulli 26, no. 3 (2020), 1989-2020
We study the problem of estimation of $N_{\gamma }(\theta )=\sum_{i=1}^{d}|\theta _{i}|^{\gamma }$ for $\gamma >0$ and of the $\ell _{\gamma }$-norm of $\theta $ for $\gamma \ge 1$ based on the observations $y_{i}=\theta _{i}+\varepsilon \xi _{i}$, $
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ef3ea3cc907adbfb6287c27fbed9950
https://hal.archives-ouvertes.fr/hal-01800810v2/document
https://hal.archives-ouvertes.fr/hal-01800810v2/document
We establish sufficient conditions of exact and almost full recovery of the node partition in Bipartite Stochastic Block Model (BSBM) using polynomial time algorithms. First, we improve upon the known conditions of almost full recovery by spectral cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3df2bc6d22b329ca55d417d39a33000
Publikováno v:
Annals of Statistics
Annals of Statistics, Institute of Mathematical Statistics, 2018, 46 (6A), pp.3130-3150. ⟨10.1214/17-AOS1653⟩
Annals of Statistics, 2018, 46 (6A), pp.3130-3150. ⟨10.1214/17-AOS1653⟩
Annals of Statistics, Institute of Mathematical Statistics, 2018, 46 (6), pp.3130-3150. ⟨10.1214/17-AOS1653⟩
Ann. Statist. 46, no. 6A (2018), 3130-3150
Annals of Statistics, Institute of Mathematical Statistics, 2018, 46 (6A), pp.3130-3150. ⟨10.1214/17-AOS1653⟩
Annals of Statistics, 2018, 46 (6A), pp.3130-3150. ⟨10.1214/17-AOS1653⟩
Annals of Statistics, Institute of Mathematical Statistics, 2018, 46 (6), pp.3130-3150. ⟨10.1214/17-AOS1653⟩
Ann. Statist. 46, no. 6A (2018), 3130-3150
International audience; We consider the problem of estimation of a linear functional in the Gaussian sequence model where the unknown vector theta is an element of R-d belongs to a class of s-sparse vectors with unknown s. We suggest an adaptive esti
Publikováno v:
Journal of the Royal Statistical Society Series B: Statistical Methodology. 79:939-956
Summary 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 mod
Autor:
Mohamed Ndaoud, Alexandre B. Tsybakov
In the context of high-dimensional linear regression models, we propose an algorithm of exact support recovery in the setting of noisy compressed sensing where all entries of the design matrix are independent and identically distributed standard Gaus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9553d9e2b9bad60fc33cbeddef0ef2e
http://arxiv.org/abs/1809.03145
http://arxiv.org/abs/1809.03145