Daskalakis, C; Dellaportas, P; Panos, A; (2022) How Good are Low-Rank Approximations in Gaussian Process Regression? In: Proceedings of 36th AAAI conference on Artificial intelligence. (pp. pp. 6463-6470). AAAI (Association for the Advancement of Artificial Intelligence): Palo Alto, CA, USA.

Preview

Text Deep_Gaussian_Processes (5).pdf - Accepted Version Download (396kB) | Preview

Abstract

We provide guarantees for approximate Gaussian Process (GP) regression resulting from two common low-rank kernel approximations: based on random Fourier features, and based on truncating the kernel's Mercer expansion. In particular, we bound the Kullback–Leibler divergence between an exact GP and one resulting from one of the afore-described low-rank approximations to its kernel, as well as between their corresponding predictive densities, and we also bound the error between predictive mean vectors and between predictive covariance matrices computed using the exact versus using the approximate GP. We provide experiments on both simulated data and standard benchmarks to evaluate the effectiveness of our theoretical bounds.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item