Review for NeurIPS paper: A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

Reviews are all on the accept side: 1 top 50% of accepted and 3 marginally above threshold. Only R4 (strong accept) intervened in the discussion. As the main reason for calling this paper borderline was limited novelty compared to [7], I had to proceed to a detailed comparative rereading of this paper to [7]. In my opinion, this approach is very different from [7]. While the authors presented it as only introducing a small modeling difference from [7], this has a huge impact on everything, in particular the resulting DNN architecture and the inference process.