Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
From MaRDI portal
Publication:1009266
DOI10.1007/s10994-008-5051-0zbMath1470.62054arXiv0803.2839OpenAlexW3101068179MaRDI QIDQ1009266
Alexandre B. Tsybakov, Arnak S. Dalalyan
Publication date: 31 March 2009
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/0803.2839
Nonparametric regression and quantile regression (62G08) Nonparametric estimation (62G05) Learning and adaptive systems in artificial intelligence (68T05)
Related Items
Entropic optimal transport is maximum-likelihood deconvolution, Aggregation via empirical risk minimization, 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation, PAC-Bayesian high dimensional bipartite ranking, Degrees of freedom for piecewise Lipschitz estimators, Exponential weights in multivariate regression and a low-rankness favoring prior, An oracle inequality for quasi-Bayesian nonnegative matrix factorization, Non-local methods with shape-adaptive patches (NLM-SAP), PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting, A reduced-rank approach to predicting multiple binary responses through machine learning, Bernstein-von Mises theorem and misspecified models: a review, User-friendly Introduction to PAC-Bayes Bounds, An efficient adaptive MCMC algorithm for pseudo-Bayesian quantum tomography, Simple proof of the risk bound for denoising by exponential weights for asymmetric noise distributions, Theory of adaptive estimation, Non-convex penalized estimation in high-dimensional models with single-index structure, Sparse regression learning by aggregation and Langevin Monte-Carlo, A new approach to estimator selection, Estimator selection with respect to Hellinger-type risks, Statistical inference in compound functional models, Bayesian fractional posteriors, Pseudo-Bayesian quantum tomography with rank-adaptation, Prediction of time series by statistical learning: general losses and fast rates, A quasi-Bayesian perspective to online clustering, Approximate models and robust decisions, Sorted concave penalized regression, On the exponentially weighted aggregate with the Laplace prior, Sharp oracle inequalities for low-complexity priors, Sampling from non-smooth distributions through Langevin diffusion, Aggregation using input-output trade-off
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Sparsity in penalized empirical risk minimization
- From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
- Learning by mirror averaging
- The Skorokhod embedding problem and its offspring
- The weighted majority algorithm
- Combining different procedures for adaptive regression
- Persistene in high-dimensional linear predictor-selection and the virtue of overparametrization
- Least angle regression. (With discussion)
- Simultaneous analysis of Lasso and Dantzig selector
- High-dimensional generalized linear models and the lasso
- Sparsity oracle inequalities for the Lasso
- Recursive aggregation of estimators by the mirror descent algorithm with averaging
- Aggregation for Gaussian regression
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
- On the Generalization Ability of On-Line Learning Algorithms
- Stable recovery of sparse overcomplete representations in the presence of noise
- Information-theoretic upper and lower bounds for statistical estimation
- Information Theory and Mixing Least-Squares Regressions
- Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
- How to use expert advice
- Adaptive Regression by Mixing
- A Statistical View of Some Chemometrics Regression Tools
- Competitive On-line Statistics
- Learning Theory and Kernel Machines
- Aggregation and Sparsity Via ℓ1 Penalized Least Squares
- A Randomized Online Learning Algorithm for Better Variance Control
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- Prediction, Learning, and Games
