Scalable inference for nonparametric stochastic approximation in reproducing kernel Hilbert spaces
再生核希尔伯特空间中非参数随机逼近的可扩展推断
Stochastic approximation (SA) is a powerful and scalable computational method for iteratively estimating the solution of optimization problems in the presence of randomness, particularly well suited for large-scale and streaming data settings. In this work we propose a theoretical framework for stochastic approximation (SA) applied to nonparametric least squares in reproducing kernel Hilbert spaces (RKHS), enabling online statistical inference in nonparametric regression…