Optimal learning with \textit{Q}-aggregation
From MaRDI portal
Publication:2448729
Abstract: We consider a general supervised learning problem with strongly convex and Lipschitz loss and study the problem of model selection aggregation. In particular, given a finite dictionary functions (learners) together with the prior, we generalize the results obtained by Dai, Rigollet and Zhang [Ann. Statist. 40 (2012) 1878-1905] for Gaussian regression with squared loss and fixed design to this learning setup. Specifically, we prove that the -aggregation procedure outputs an estimator that satisfies optimal oracle inequalities both in expectation and with high probability. Our proof techniques somewhat depart from traditional proofs by making most of the standard arguments on the Laplace transform of the empirical process to be controlled.
Recommendations
- Deviation optimal learning using greedy \(Q\)-aggregation
- \({\mathcal Q}\)-learning
- Reinforcement learning via approximation of the Q-function
- Adaptive aggregation for reinforcement learning in average reward Markov decision processes
- Approximate policy iteration for Markov decision processes via quantitative adaptive aggregations
- Adaptive Q-learning
- Q-Learning with Linear Function Approximation
- Optimal learning with non-Gaussian rewards
- Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality
- Optimal learning with Bernstein online aggregation
Cites work
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- Aggregation for Gaussian regression
- Aggregation via empirical risk minimization
- Combining different procedures for adaptive regression
- Convexity, Classification, and Risk Bounds
- Deviation optimal learning using greedy \(Q\)-aggregation
- Exponential screening and optimal rates of sparse estimation
- Fast learning rates in statistical inference through aggregation
- Functional aggregation for nonparametric regression.
- scientific article; zbMATH DE number 439380 (Why is no real title available?)
- scientific article; zbMATH DE number 5544465 (Why is no real title available?)
- scientific article; zbMATH DE number 49190 (Why is no real title available?)
- Kullback-Leibler aggregation and misspecified generalized linear models
- Learning by mirror averaging
- Learning Theory and Kernel Machines
- Mirror averaging with sparsity priors
- Mixing strategies for density estimation.
- On concentration of self-bounding functions
- Optimal aggregation of classifiers in statistical learning.
- Optimal rates of aggregation in classification under low noise assumption
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- PAC-Bayesian bounds for sparse regression estimation with exponential weights
- Sharp oracle inequalities for aggregation of affine estimators
- Sharper lower bounds on the performance of the empirical risk minimization algorithm
- Sparse estimation by exponential weighting
- Sparse regression learning by aggregation and Langevin Monte-Carlo
- Statistical inference in compound functional models
- Suboptimality of Penalized Empirical Risk Minimization in Classification
Cited in
(14)- Optimal bounds for aggregation of affine estimators
- Aggregating estimates by convex optimization
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- On aggregation for heavy-tailed classes
- Aggregation of affine estimators
- Performance of empirical risk minimization in linear aggregation
- Fast rates for general unbounded loss functions: from ERM to generalized Bayes
- An adaptive multiclass nearest neighbor classifier
- Transfer Learning in Large-Scale Gaussian Graphical Models with False Discovery Rate Control
- Targeting underrepresented populations in precision medicine: a federated transfer learning approach
- Robust angle-based transfer learning in high dimensions
- Deviation optimal learning using greedy \(Q\)-aggregation
- Precise asymptotics of bagging regularized M-estimators
- Optimal learning with Bernstein online aggregation
This page was built for publication: Optimal learning with \textit{Q}-aggregation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2448729)
