Concentration of weakly dependent Banach-valued sums and applications to statistical learning methods
From MaRDI portal
Publication:2325378
DOI10.3150/18-BEJ1095zbMath1428.62185arXiv1712.01934OpenAlexW2976093751MaRDI QIDQ2325378
Gilles Blanchard, Oleksandr Zadorozhnyi
Publication date: 25 September 2019
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1712.01934
Inequalities; stochastic orderings (60E15) Learning and adaptive systems in artificial intelligence (68T05) Probability theory on linear topological spaces (60B11)
Related Items
Exponential inequalities for nonstationary Markov chains, Factor models for high‐dimensional functional time series II: Estimation and forecasting
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Inference for functional data with applications
- Two oracle inequalities for regularized boosting classifiers
- Moment bounds for dependent sequences in smooth Banach spaces
- Deviation inequalities for sums of weakly dependent time series
- Optimal rates for regularization of statistical inverse learning problems
- Extensions of the Hoeffding-Azuma inequalities
- On regularization algorithms in learning theory
- Basic properties of strong mixing conditions. A survey and some open questions
- On tail probabilities for martingales
- Correlation inequalities on some partially ordered sets
- A new mixing notion and functional central limit theorems for a sieve bootstrap in time series
- Linear processes in function spaces. Theory and applications
- A new weak dependence condition and applications to moment inequalities
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Measure concentration for Euclidean distance in the case of dependent random variables.
- Sums and Gaussian vectors
- Optimum bounds for the distributions of martingales in Banach spaces
- About the Berry-Esseen theorem for weakly dependent sequences
- Vector-valued reproducing kernel Banach spaces with applications to multi-task learning
- A Bernstein-type inequality for some mixing processes and dynamical systems with an application to learning
- Fréchet differentiability of \(\mathcal{S}^p\) norms
- Optimal rates for the regularized least-squares algorithm
- Rate of convergence for Hilbert space valued processes
- Exponential inequalities for martingales with applications
- Concentration inequalities for dependent random variables via the martingale method
- Maximal margin classification for metric spaces
- Weak dependence. With examples and applications.
- Bernstein inequality and moderate deviations under strong mixing conditions
- Reproducing Kernel Banach Spaces with the ℓ1 Norm II: Error Analysis for Regularized Least Square Regression
- A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION
- On Strong Mixing Conditions for Stationary Gaussian Processes
- Non-strong mixing autoregressive processes
- DISCRETIZATION ERROR ANALYSIS FOR TIKHONOV REGULARIZATION
- EXPONENTIAL INEQUALITIES AND FUNCTIONAL ESTIMATIONS FOR WEAK DEPENDENT DATA: APPLICATIONS TO DYNAMICAL SYSTEMS
- Remarks on Inequalities for Large Deviation Probabilities
- Bernstein-type large deviations inequalities for partial sums of strong mixing processes
- Regularized learning schemes in feature Banach spaces
- Learning Theory
- Invariance principles for dependent variables
- Probability Inequalities for Sums of Bounded Random Variables
- Association of Random Variables, with Applications
- On an Infinite-Dimensional Version of S. N. Bernstein’s Inequalities
- On the dual formulation of regularized linear systems with convex risks
