Infinite-dimensional spherical-radial decomposition for probabilistic functions, with application to constrained optimal control and Gaussian process regression
The spherical-radial decomposition (SRD) is an efficient method for estimating probabilistic functions and their gradients defined over finite-dimensional elliptical distributions. In this work, we generalize the SRD to infinite stochastic dimensions by combining subspace SRD with standard Monte Carlo methods. The resulting method, which we call hybrid infinite-dimensional SRD (hiSRD) provides an unbiased, low-variance estimator for convex sets arising, for instance, in chance-constrained optimization. We provide a theoretical analysis of the variance of finite-dimensional SRD as the dimension increases, and show that the proposed hybrid method eliminates truncation-induced bias, reduces variance, and allows the computation of derivatives of probabilistic functions. We present comprehensive numerical studies for a risk-neutral stochastic PDE optimal control problem with joint chance state constraints, and for optimizing kernel parameters in Gaussian process regression under the constraint that the posterior process satisfies joint chance constraints.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Differentiability and Approximation of Probability Functions under Gaussian Mixture Models: A Bayesian Approach
In this work, we study probability functions associated with Gaussian mixture models. Our primary focus is on extending the use of spherical radial decomposition for multivariate Gaussian random vectors to the context of…
Truncated Kernel Stochastic Gradient Descent with General Losses and Spherical Radial Basis Functions
In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compared to traditional kernel SGD, our algorithm improves efficiency and scal…
Cascaded Light Propagation Volumes using Spherical Radial Basis Functions
This paper introduces a contribution made to one of the newest methods for simulating indirect lighting in dynamic scenes , the cascaded light propagation volumes . Our contribution consists on using Spherical Radial Bas…
Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality
In this note, we study how neural networks with a single hidden layer and ReLU activation interpolate data drawn from a radially symmetric distribution with target labels 1 at the origin and 0 outside the unit ball, if n…
Tensor Decomposition Meets RKHS: Efficient Algorithms for Smooth and Misaligned Data
The canonical polyadic (CP) tensor decomposition decomposes a multidimensional data array into a sum of outer products of finite-dimensional vectors. Instead, we can replace some or all of the vectors with continuous fun…
Tensor Decomposition