PAC-Bayes Analysis of Multi-view Learning
This work provides incremental theoretical tools for researchers in multi-view learning, offering bounds applicable to both supervised and semi-supervised settings.
This paper tackles the problem of analyzing generalization performance in multi-view learning by presenting eight PAC-Bayes bounds that incorporate data-dependent Gaussian priors to emphasize view agreements, and evaluates them on benchmark data compared to single-view bounds.
This paper presents eight PAC-Bayes bounds to analyze the generalization performance of multi-view classifiers. These bounds adopt data dependent Gaussian priors which emphasize classifiers with high view agreements. The center of the prior for the first two bounds is the origin, while the center of the prior for the third and fourth bounds is given by a data dependent vector. An important technique to obtain these bounds is two derived logarithmic determinant inequalities whose difference lies in whether the dimensionality of data is involved. The centers of the fifth and sixth bounds are calculated on a separate subset of the training set. The last two bounds use unlabeled data to represent view agreements and are thus applicable to semi-supervised multi-view learning. We evaluate all the presented multi-view PAC-Bayes bounds on benchmark data and compare them with previous single-view PAC-Bayes bounds. The usefulness and performance of the multi-view bounds are discussed.