Kernel Stein Discrepancy
A tool that measures the difference between two distributions through the Stein operator and functions in an RKHS. It can be computed without knowing the normalization constant and can be estimated from samples alone.
Timeline (last 90 days)
The kernel Stein discrepancy can be computed without knowing the normalization constant, offering a new idea for constructing RDP certificates.
The kernel Stein discrepancy measures the difference between two distributions via the Stein operator and functions in a reproducing kernel Hilbert space, can be computed from samples alone, and is insensitive to the normalization constant.
All Facts (2)
The kernel Stein discrepancy can be computed without knowing the normalization constant, offering a new idea for constructing RDP certificates.
50%UnverifiedThe kernel Stein discrepancy measures the difference between two distributions via the Stein operator and functions in a reproducing kernel Hilbert space, can be computed from samples alone, and is insensitive to the normalization constant.
50%