Skip to yearly menu bar Skip to main content


Talk

Spherical Structured Feature Maps for Kernel Approximation

Yueming LYU

C4.8

Abstract: We propose Spherical Structured Feature (SSF) maps to approximate shift and rotation invariant kernels as well as bth-order arc-cosine kernels~\cite{cho2009kerneldeeplearning}. We construct SSF maps based on the point set on d1 dimensional sphere Sd1. We prove that the inner product of SSF maps are unbiased estimates for above kernels if asymptotically uniformly distributed point set on Sd1 is given. According to ~\cite{brauchart2015distributing}, optimizing the discrete Riesz s-energy can generate asymptotically uniformly distributed point set on Sd1. Thus, we propose an efficient coordinate decent method to find a local optimum of the discrete Riesz s-energy for SSF maps construction. Theoretically, SSF maps construction achieves linear space complexity and loglinear time complexity. Empirically, SSF maps achieve superior performance compared with other methods.

Live content is unavailable. Log in and register to view live content