Fetching the paper…
Reading the bibliography…
In batch learning, stability together with existence and uniqueness of the solution corresponds to well-posedness of Empirical Risk Minimization (ERM) methods; recently, it was proved that CV_loo stability is necessary and sufficient for generalization and consistency of ERM.
Random Iterative Models
M. Duflo · 1991
Earlier work this paper cites.
Scale-sensitive dimensions, uniform convergence, and learnability
N. Alon, S. Ben-David, N. Cesa-Bianchi, and D. Haussler · 1997
Earlier work this paper cites.
Stability and generalization
O. Bousquet and A. Elisseeff · 2001
Earlier work this paper cites.
General conditions for predictivity in learning theory
S. Mukherjee T. Poggio, R. Rifkin and P. Niyogi · 2004
Cited alongside, same era.
A central limit theorem for robbins monro algorithms with projections
J. Lelong · 2005
Cited alongside, same era.
Stability results in learning theory
S. Mukherjee Rakhlin, A. and T. Poggio · 2005
Cited alongside, same era.
Sufficient conditions for uniform stability of regularization algorithms
A. Wibisono, L. Rosasco, and T. Poggio
Cited in the paper.
Learning theory: Stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
T. Poggio S. Mukherjee P. Niyogi and R. Rifkin · 2006
Later among the works it cites.
Lecture notes on online learning
A. Rakhlin · 2010
Later among the works it cites.
Learnability, stability and uniform convergence
N. Srebro S. Shalev-Shwartz, O. Shamir and K. Sridharan · 2010
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…