We are experiencing minor difficulties with our submission forms, which we are working to resolve. If you have any issues while submitting items, please contact us at dspace-lib@mit.edu.
Solutions of learning problems by Empirical Risk Minimization (ERM) need to be consistent, so that they may be predictive. They also need to be well-posed, so that they can be used robustly. We show that a statistical form of well-posedness, defined in terms of the key property of L-stability, is necessary and sufficient for consistency of ERM.
