Timezone: »

Poster
Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
Yingyi Ma · Vignesh Ganapathiraman · Yaoliang Yu · Xinhua Zhang

Thu Jul 16 06:00 AM -- 06:45 AM &amp; Thu Jul 16 06:00 PM -- 06:45 PM (PDT) @ None #None

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 \emph{convex} representation learning algorithm for a variety of generalized invariances that can be modeled as semi-norms. Novel Euclidean embeddings are introduced for kernel representers in a semi-inner-product space, and approximation bounds are established. This allows invariant representations to be learned efficiently and effectively as confirmed in our experiments, along with accurate predictions.