A New Perspective On Learning Linear Separators With Large Lqlp Margins

We give theoretical and empirical results that provide new insights into large margin learning. We prove a bound on the generalization error of learning linear separators with large LqLp margins (where L-q and L-p are dual norms) for any finite p >= 1. The bound leads to a simple data-dependent sufficient condition for fast learning in addition to extending and improving upon previous results. We also provide the first study that shows the benefits of taking advantage of margins with p < 2 over margins with p >= 2. Our experiments confirm that our theoretical results are relevant in practice.