PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting

DOI10.1016/j.jmva.2018.12.004zbMath1417.62086OpenAlexW2614938855WikidataQ115570110 ScholiaQ115570110MaRDI QIDQ2418515

Christophe Chesneau, Tung Duy Luu, Jalal Fadili

Publication date: 27 May 2019

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmva.2018.12.004

zbMATH Keywords

framehigh-dimensional regressionsparse learningexponential weighted aggregationforward-backward Langevin Monte Carlogroup-analysis sparsitysparse oracle inequality

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Monte Carlo methods (65C05)

Related Items (3)

User-friendly Introduction to PAC-Bayes Bounds ⋮ Sharp oracle inequalities for low-complexity priors ⋮ Sampling from non-smooth distributions through Langevin diffusion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bagging predictors
• Nonlinear total variation based noise removal algorithms
• Smoothing proximal gradient method for general structured sparse regression
• Sparse regression learning by aggregation and Langevin Monte-Carlo
• Mirror averaging with sparsity priors
• Statistics for high-dimensional data. Methods, theory and applications.
• On the layered nearest neighbour estimate, the bagged nearest neighbour estimate and the random forest method in regression and classification
• Exponentiated gradient versus gradient descent for linear predictors
• Deviation optimal learning using greedy \(Q\)-aggregation
• Linear and convex aggregation of density estimators
• Variable selection in nonparametric additive models
• Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
• A simple proof of the Poincaré inequality for a large class of probability measures
• High-dimensional additive modeling
• Stein block thresholding for image denoising
• Bayesian inference in wavelet-based models
• The weighted majority algorithm
• Exponential convergence of Langevin distributions and their discrete approximations
• Ridgelets: estimating with ridge functions
• Aggregating regression procedures to improve performance
• Boosting a weak learning algorithm by majority
• Sharp oracle inequalities for aggregation of affine estimators
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Simultaneous adaptation to the margin and to complexity in classification
• Proximal Markov chain Monte Carlo algorithms
• Adapting to Unknown Smoothness via Wavelet Shrinkage
• Information Theory and Mixing Least-Squares Regressions
• Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing
• The Group Lasso for Logistic Regression
• Ideal spatial adaptation by wavelet shrinkage
• Variational Analysis
• New tight frames of curvelets and optimal representations of objects with piecewise C² singularities
• A Hamiltonian Monte Carlo Method for Non-Smooth Energy Sampling
• Sparse Additive Models
• Sparsity and Smoothness Via the Fused Lasso
• Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities
• Model Selection and Estimation in Regression with Grouped Variables
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Random forests
• Sparse estimation by exponential weighting

This page was built for publication: PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting