A Proof of Proposition 1 We first follow the proof of the log-sum inequality to prove the following inequality: q u (y |D r) log q u (y |D

Define the function f (t) null t log t which is convex. This section discusses the sparse GP model that is used in the classification of the synthetic moon dataset in Sec. A GP is fully specified by its prior mean (i.e., assumed to be Given the latent function values (i.e., also known as inducing variables) On the other hand, Figs. 9 and 10 visualize the approximate posterior beliefs Let us consider the experiment in Sec. Figure 1 shows results of averaged KL divergences (i.e., performance metric described in Sec. 4) achieved by EUBO, rKL, and However, the fourth row of Table 3 shows that both EUBO and rKL do not perform that well. EUBO may suffer from poor unlearning performance when λ is too small. One may wonder how our unlearning methods can handle multiple users' request arriving sequentially Figure 12: Graphs of averaged KL divergence vs.