Timezone: »

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 & 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.

Author Information

Yingyi Ma (UIC)
Vignesh Ganapathiraman (University of Illinois at Chicago)
Yaoliang Yu (University of Waterloo)
Xinhua Zhang (University of Illinois at Chicago (UIC))

More from the Same Authors