SOURCE-LINKED INTELLIGENCE

Sharp margin-based generalization bounds for realizable SVM

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Let the exact homogeneous hard-margin support vector machine be trained on \(m\) independent observations from a Borel probability law on a real Hilbert space. We prove that, with score zero counted as an error, there is a universal numerical constant \(C\) such that \[ \Pp\left( γ_m>0,\quad \Risk(u_m)> \frac{C}{m} \left( K_m+\log\frac1δ \right) \right) \le δ. \] Here \(γ_m\) is the empirical homogeneous margin, \(u_m\) is the exact minimum-norm unit-margin separator, \(r_m\) is the largest training radius, and \(K_m:=r_m^2\norm{u_m}^2=r_m^2/γ_m^2\) on \(\{γ_m>0\}\). The proof is driven by a d

Read original source ↗ Open in workspace

recordType

paper

region

Global