A unifying representer theorem for inverse problems and machine learning
This work provides a foundational framework for regularization in optimization, potentially impacting all of ML/AI by unifying disparate results, though it is incremental in extending existing theories.
The authors tackled the problem of unifying regularization approaches for ill-posed inverse problems and machine learning by proposing a general representer theorem in Banach spaces, which recovers known results like RKHS representer theorems and sparsity-promoting functionals, as well as new ones.
The standard approach for dealing with the ill-posedness of the training problem in machine learning and/or the reconstruction of a signal from a limited number of measurements is regularization. The method is applicable whenever the problem is formulated as an optimization task. The standard strategy consists in augmenting the original cost functional by an energy that penalizes solutions with undesirable behavior. The effect of regularization is very well understood when the penalty involves a Hilbertian norm. Another popular configuration is the use of an $\ell_1$-norm (or some variant thereof) that favors sparse solutions. In this paper, we propose a higher-level formulation of regularization within the context of Banach spaces. We present a general representer theorem that characterizes the solutions of a remarkably broad class of optimization problems. We then use our theorem to retrieve a number of known results in the literature---e.g., the celebrated representer theorem of machine leaning for RKHS, Tikhonov regularization, representer theorems for sparsity promoting functionals, the recovery of spikes---as well as a few new ones.