It is a commonly held belief that enforcing invariance improves generalisation. Although this approach enjoys widespread popularity, it is only very recently that a rigorous theoretical demonstration of this benefit has been established. In this work we build on the function space perspective of Elesedy and Zaidi arXiv:2102.10333 to derive a strictly non-zero generalisation benefit of incorporating invariance in kernel ridge regression when the target is invariant to the action of a compact group. We study invariance enforced by feature averaging and find that generalisation is governed by a notion of effective dimension that arises from the interplay between the kernel and the group. In building towards this result, we find that the action of the group induces an orthogonal decomposition of both the reproducing kernel Hilbert space and its kernel, which may be of interest in its own right.
翻译:人们普遍认为,强制实施不轨做法可以改善一般情况。虽然这种做法受到普遍欢迎,但直到最近才对这种好处进行了严格的理论示范。在这项工作中,我们利用Elesdy和Zaidi arXiv的功能空间视角:2102.10333,以获得在目标与一个集约集团的行动不相容时将不轨现象纳入内核脊回归的严格非零普遍性效益。我们研究平均特征的不轨做法,发现一般做法受内核与集团相互作用所产生的有效层面概念的制约。在朝着这一结果发展的过程中,我们发现该组的行动导致产生产物的内核Hilbert空间及其内核的反向分解,这可能对其本身的权利有利。