We proceed to show the sparsistency510 of the estimated parameters. First, suppose that Θ t;ij 6= 0 for some time tand index (i,j). Due to 0 < γ < 1, the above inequality implies that bΘt;ij = 0521 for every t and (i,j) 6 St, and bΘt;ij bΘt 1;ij = 0 for every t > 0 and (i,j) 6 Dt. The proof is inspired527 by Corollary 1 in [47]. First, we present the following key lemmas.528

This section provides a brief introduction to sparse variational approximation for variationally sparse GP (SVGP). We use regression as a running example, but the principles of SVGP also apply to other supervised learning tasks such as classification. Readers are also referred to e.g.

We begin with a simple lemma showing that the values of the levels are monotone: Lemma A.1. First, we note that the second part of the lemma holds by lines 15-16. Let zil and zih be the value of zland zhin Algorithm 2 on line 9 on window i. There are two cases, depending on whether an element e? was added to the solutions or not. Suppose no element e? was added to the solution. Then all the levels remain the same.