We thank the reviewers for their time and effort reviewing our paper. We are pleased that you found our work to "solve At the latest, source code will be made publicly available upon publication. When we write "greedy," we are referring to the sequential setting When we say "naive batch" we We will add a thorough discussion on this topic to a future version of the paper. We will update the section accordingly. The main issue is how to do this efficiently for complex, non-linear models.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper defines a joint generative model of an image and its annotated text which is used to learn a bit vector representation for large scale image retrieval. An Indian Buffet Process is used to learn the length of the bit vector. The method is compared favourably to several widely used techniques. Quality ======= It is good to see a retrieval paper constructed around a well-defined probabilistic model.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Stochastic variational inference (SVI) requires careful selection of a step size. This paper proposes a Kalman filter to set the step size automatically. The authors show that standard Gaussian KF does not satisfy the Robbins Munro criteria (and performs badly). They propose to apply a KF based on T-distributions, and show that this gives better results than standard SVI.

The reviewer seems to have clearly understood the approach and our intended contribution. We feel that the reviewer's objections mostly involve technical issues that we did not explain or justify clearly enough, but which do not undermine the novelty or soundness of the basic results. We apologize for not explaining / justifying these issues more carefully, and feel they will be straightforward to address in the revision. We thank the reviewer for raising them.

In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning.

Information Processing Systems 34, page to appear.

Recent work in variational inference (VI) uses ideas from Monte Carlo estimation to tighten the lower bounds on the log-likelihood that are used as objectives.

Neural Information Processing Systems http://nips.cc/