Virtualconference
H De-biasing arbitrary convex regularizers and asymptotic normality
Auteurs : Bellec, Pierre C. (Auteur de la Conférence)
CIRM (Editeur )
CIRM (Editeur )
-
[Virtualconference]
Experimenting in equilibrium
/ Auteur de la Conférence Wager, Stefan.
CIRM
-
[Virtualconference]
Structure learning for CTBN's
/ Auteur de la Conférence Miasojedow, Błażej.
CIRM
-
[Virtualconference]
The price of competition: effect size heterogeneity matters in high dimensions!
/ Auteur de la Conférence Wang, Hua.
CIRM
-
[Virtualconference]
Scaling of scoring rules
/ Auteur de la Conférence Wallin, Jonas.
CIRM
-
[Virtualconference]
Hierarchical bayes modeling for large-scale inference
/ Auteur de la Conférence Yekutieli, Daniel.
CIRM
-
[Virtualconference]
Change: detection, estimation, segmentation
/ Auteur de la Conférence Siegmund, David.
CIRM
-
[Virtualconference]
High-dimensional, multiscale online changepoint detection
/ Auteur de la Conférence Samworth, Richard.
CIRM
-
[Virtualconference]
The smoothed multivariate square-root Lasso: an optimization lens on concomitant estimation
/ Auteur de la Conférence Salmon, Joseph.
CIRM
-
[Virtualconference]
Knockoff genotypes: value in counterfeit
/ Auteur de la Conférence Sabatti, Chiara.
CIRM
-
[Virtualconference]
Optimal and maximin procedures for multiple testing problems
/ Auteur de la Conférence Rosset, Saharon.
CIRM
-
[Virtualconference]
Sparse multiple testing: can one estimate the null distribution ?
/ Auteur de la Conférence Roquain, Etienne.
CIRM
-
[Virtualconference]
Bayesian spatial adaptation
/ Auteur de la Conférence Rockova, Veronika.
CIRM
-
[Virtualconference]
Universal inference using the split likelihood ratio test
/ Auteur de la Conférence Ramdas, Aaditya K..
CIRM
-
[Virtualconference]
How to estimate a density on a spider web ?
/ Auteur de la Conférence Picard, Dominique.
CIRM
-
[Virtualconference]
Post hoc bounds on false positives using reference families
/ Auteur de la Conférence Neuvial, Pierre.
CIRM
-
[Virtualconference]
Quasi logistic distributions and Gaussian scale mixing
/ Auteur de la Conférence Letac, Gerard.
CIRM
-
[Virtualconference]
Shrinkage estimation of mean for complex multivariate normal distribution with unknown covariance when p > n
/ Auteur de la Conférence Konno, Yoshihiko.
CIRM
-
[Virtualconference]
Treatment effect estimation with missing attributes
/ Auteur de la Conférence Josse, Julie.
CIRM
-
[Virtualconference]
Floodgate: inference for model-free variable importance
/ Auteur de la Conférence Janson, Lucas.
CIRM
-
[Virtualconference]
On Cholesky structures on real symmetric matrices and their applications
/ Auteur de la Conférence Ishi, Hideyuki.
CIRM
-
[Virtualconference]
Optimal control of false discovery criteria in the general two-group model
/ Auteur de la Conférence Heller, Ruth.
CIRM
-
[Virtualconference]
Isotonic Distributional Regression (IDR) - leveraging monotonicity, uniquely so!
/ Auteur de la Conférence Gneiting, Tilmann.
CIRM
-
[Virtualconference]
Consistent model selection criteria and goodness-of-fit test for common time series models
/ Auteur de la Conférence Bardet, Jean-Marc.
CIRM
-
[Virtualconference]
High-dimensional classification by sparse logistic regression
/ Auteur de la Conférence Abramovich, Felix.
CIRM
- BELLEC, Pierre C. et ZHANG, Cun-Hui. Second order Poincar\'e inequalities and de-biasing arbitrary convex regularizers when $ p/n\to\gamma$. arXiv preprint arXiv:1912.11943, 2019. - https://arxiv.org/abs/1912.11943
- BELLEC, Pierre C. et ZHANG, Cun-Hui. De-biasing the lasso with degrees-of-freedom adjustment. arXiv preprint arXiv:1902.08885, 2019. - https://arxiv.org/abs/1902.08885
Loading the player...
Résumé :
A new Central Limit Theorem (CLT) is developed for random variables of the form ξ=z⊤f(z)−divf(z) where z∼N(0,In).
The normal approximation is proved to hold when the squared norm of f(z) dominates the squared Frobenius norm of ∇f(z) in expectation.
Applications of this CLT are given for the asymptotic normality of de-biased estimators in linear regression with correlated design and convex penalty in the regime p/n→γ∈(0,∞). For the estimation of linear functions ⟨a,β⟩ of the unknown coefficient vector β, this analysis leads to asymptotic normality of the de-biased estimate for most normalized directions a0, where "most" is quantified in a precise sense. This asymptotic normality holds for any coercive convex penalty if γ<1 and for any strongly convex penalty if γ≥1. In particular the penalty needs not be separable or permutation invariant.
The normal approximation is proved to hold when the squared norm of f(z) dominates the squared Frobenius norm of ∇f(z) in expectation.
Applications of this CLT are given for the asymptotic normality of de-biased estimators in linear regression with correlated design and convex penalty in the regime p/n→γ∈(0,∞). For the estimation of linear functions ⟨a,β⟩ of the unknown coefficient vector β, this analysis leads to asymptotic normality of the de-biased estimate for most normalized directions a0, where "most" is quantified in a precise sense. This asymptotic normality holds for any coercive convex penalty if γ<1 and for any strongly convex penalty if γ≥1. In particular the penalty needs not be separable or permutation invariant.
Keywords : M-estimators; convex regularization; asymptotic normality; confidence intervals; de-biasing
Codes MSC :
Ressources complémentaires :
https://www.cirm-math.fr/RepOrga/2146/Slides/Bellec_slides.pdf
|
Informations sur la Vidéo
Réalisateur : Hennenfent, GuillaumeLangue : Anglais Date de publication : 15/06/2020 Date de captation : 05/06/2020 Collection : Research talks ; Probability and Statistics Durée : 00:46:32 Domaine : Probability & Statistics Audience : Chercheurs ; Doctorants , Post - Doctorants Download : https://videos.cirm-math.fr/ 2020-06-05_Bellec.mp4 
|
Informations sur la Rencontre Virtuelle
Nom de la rencontre : Mathematical Methods of Modern Statistics 2 / Méthodes mathématiques en statistiques modernes 2Organisateurs de la rencontre : Bogdan, Malgorzata ; Graczyk, Piotr ; Panloup, Fabien ; Proïa, Frédéric ; Roquain, Etienne Dates : 15/06/2020 - 19/06/2020 Année de la rencontre : 2020 URL Congrès : https://www.cirm-math.com/cirm-virtual-...
Citation Data
DOI : 10.24350/CIRM.V.19640503Cite this video as: Bellec, Pierre C. (2020). De-biasing arbitrary convex regularizers and asymptotic normality.CIRM . Audiovisual resource. doi:10.24350/CIRM.V.19640503 URI : http://dx.doi.org/10.24350/CIRM.V.19640503 |
Voir aussi
Bibliographie
Z
