Obtaining fast error rates in nonconvex situations
From MaRDI portal
Publication:933417
DOI10.1016/j.jco.2007.09.001zbMath1338.60112OpenAlexW1989007039MaRDI QIDQ933417
Publication date: 21 July 2008
Published in: Journal of Complexity (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.jco.2007.09.001
Approximations to statistical distributions (nonasymptotic) (62E17) Applications of functional analysis in probability theory and statistics (46N30) Prediction theory (aspects of stochastic processes) (60G25)
Related Items
Regularization in kernel learning ⋮ Learning without concentration for general loss functions ⋮ Unnamed Item ⋮ On the optimality of the empirical risk minimization procedure for the convex aggregation problem ⋮ General oracle inequalities for model selection ⋮ On the optimality of the aggregate with exponential weights for low temperatures ⋮ General nonexact oracle inequalities for classes with a subexponential envelope ⋮ Error analysis of multicategory support vector machine classifiers
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On the uniform convexity of \(L^p\) and \(l^p\)
- Convexity of Chebyshev sets
- Optimal aggregation of classifiers in statistical learning.
- Weak convergence and empirical processes. With applications to statistics
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Empirical minimization
- Local Rademacher complexities
- Theory of Classification: a Survey of Some Recent Advances
- Lower Bounds for the Empirical Minimization Algorithm
- APPROXIMATIVE PROPERTIES OF SETS IN NORMED LINEAR SPACES
- Uniform Central Limit Theorems
- Scale-sensitive dimensions, uniform convergence, and learnability
- The importance of convexity in learning with squared loss
- Neural Network Learning