A characterization of multioutput learnability
From MaRDI portal
Cites work
- scientific article; zbMATH DE number 3446442 (Why is no real title available?)
- 10.1162/153244303321897690
- A Vector-Contraction Inequality for Rademacher Complexities
- A characterization of multiclass learnability
- A theory of the learnable
- Adaptive multivariate ridge regression
- Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
- Combinatorics of random processes and sections of convex bodies
- Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
- Exploiting label dependencies for improved sample complexity
- Fat-shattering and the learnability of real-valued functions
- Groups, graphs and random walks. Selected papers of the workshop, Cortona, Italy, June 2--6, 2014 on the occasion of the 60th birthday of Wolfgang Woess
- Kernels for vector-valued functions: a review
- Local Rademacher complexity-based learning guarantees for multi-task learning
- Neural Network Learning
- On Learning Vector-Valued Functions
- On label dependence and loss minimization in multi-label classification
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Online learning via sequential complexities
- Prediction, Learning, and Games
- Scale-sensitive dimensions, uniform convergence, and learnability
- Sequential complexities and uniform martingale laws of large numbers
- The Nonstochastic Multiarmed Bandit Problem
- The theory of least squares when the parameters are stochastic and its application to the analysis of growth curves
- Toward efficient agnostic learning
- Towards empirical process theory for vector-valued functions: metric entropy of smooth function classes
- Understanding machine learning. From theory to algorithms
This page was built for publication: A characterization of multioutput learnability
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7029039)
