The regularized least squares algorithm and the problem of learning halfspaces
From MaRDI portal
Publication:1944907
DOI10.1016/j.ipl.2011.01.011zbMath1260.68189MaRDI QIDQ1944907
Publication date: 28 March 2013
Published in: Information Processing Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.ipl.2011.01.011
computational complexity; computational learning theory; analysis of algorithms; kernel; halfspaces; regularized least squares algorithm
68Q32: Computational learning theory
68Q25: Analysis of algorithms and problem complexity
68Q17: Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Learning intersections and thresholds of halfspaces
- An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution
- Halfspace learning, linear programming, and nonmalicious distributions
- Optimal aggregation of classifiers in statistical learning.
- Optimum bounds for the distributions of martingales in Banach spaces
- Learning theory estimates via integral operators and their approximations
- On early stopping in gradient descent learning
- On the mathematical foundations of learning
- Efficient noise-tolerant learning from statistical queries
- Agnostically Learning Halfspaces
- Theory of Reproducing Kernels
- Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
