Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
ICML, pp. 6532-6542, 2020.
We introduced a new framework of representation learning where an reproducing kernel Hilbert space is turned into a semi-inner-product space via a semi-norm regularizer
Invariance (defined in a general sense) has been one of the most effective priors for representation learning. Direct factorization of parametric models is feasible only for a small range of invariances, while regularization approaches, despite improved generality, lead to nonconvex optimization. In this work, we develop a convex repres...More
PPT (Upload PPT)