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

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper describes a Bayesian model for online learning in the context of random forests models for supervised classification. The main contribution of the paper is the formulation of a novel prior on binary rooted trees that relies on the Mondrian process. An additional novelty of the paper is the use of hierarchical normalized stable processes as priors for the probabilities of the different classes at each terminal node. The paper is well written and the formulation novel.

We provide a detailed proof for Theorem 1. We provide an alternative proof for identifiability of Poisson BN. I (G D), where the last equality holds because the integrand is the kernel of a beta distribution. The scRNA-seq experiments were performed on five mice with AhR knockout targeted to intestinal stem cells. On average each mouse contributed 6,000 cells.

Multivariate zero-inflated count data arise in a wide range of areas such as economics, social sciences, and biology.

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

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes a method to recover signals from compressive measurements. The method consists of jointly estimating the signal and a Gaussian Mixture Model (GMM) capable of representing it succinctly. The main contribution of the paper is the idea of imposing a sparse structure on the GMM adapted to the case when the signal of interest corresponds to image patches. This is further exploited by a more structured prior that promotes an appropriate group-sparsity pattern (essentially interactions between adjoining pixels are not penalized by the sparsity-inducing penalty).

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

In various experiments, our Bayesian SPNs often improve test likelihoods over greedy SPN learners.

Achieving the full promise of the Thermodynamic V ariational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann integral approximation, requires choosing a "schedule" of sorted discretization points. This paper introduces a bespoke Gaussian process bandit optimization method for automatically choosing these points. Our approach not only automates their one-time selection, but also dynamically adapts their positions over the course of optimization, leading to improved model learning and inference. We provide theoretical guarantees that our bandit optimization converges to the regret-minimizing choice of integration points. Empirical validation of our algorithm is provided in terms of improved learning and inference in V ariational Autoencoders and Sigmoid Belief Networks.