14.2 Quadratic hinge loss stability. Let L denote the quadratic hinge loss function de ned for all...
Question:
14.2 Quadratic hinge loss stability. Let L denote the quadratic hinge loss function dened for all y 2 f+1;????1g and y0 2 R by L(y0; y) =
(
0 if 1 ???? y0y 0;
(1 ???? y0y)2 otherwise:
Assume that L(h(x); y) is bounded by M, 1 M < 1, for all h 2 H, x 2 X, and y 2 f+1;????1g, which also implies a bound on jh(x)j for all h 2 H and x 2 X.
Derive a stability-based generalization bound for SVMs with the quadratic hinge loss.
Fantastic news! We've Found the answer you've been seeking!
Step by Step Answer:
Related Book For
Foundations Of Machine Learning
ISBN: 9780262351362
2nd Edition
Authors: Mehryar Mohri, Afshin Rostamizadeh
Question Posted: