We present discretize_distributions, a Python package that efficiently constructs discrete approximations of Gaussian mixture distributions and provides guarantees on the approximation error in Wasserstein distance. The package implements state-of-the-art quantization methods for Gaussian mixture models and extends them to improve scalability. It further integrates complementary quantization strategies such as sigma-point methods and provides a modular interface that supports custom schemes and integration into control and verification pipelines for cyber-physical systems. We benchmark the package on various examples, including high-dimensional, large, and degenerate Gaussian mixtures, and demonstrate that discretize_distributions produces accurate approximations at low computational cost.

The paper presents several "shadowing" results for gradient descent and the heavy ball method, under several conditions on the objective. In short, the authors provide conditions under which a discrete approximation of an ODE defines a trajectory that "stays close" to the actual trajectory of the ODE. This research is motivated by a by a recent paper by Su, Jordan, and Candes that models Nesterov's method via an ODE: this leads the authors to ask the question of when an ODE solution indeed well approximates a discrete algorithm, which is what would be implemented in practice. Although the interest and motivation is mostly on HB, the bulk of the results presented in the paper are for GD. The paper is well-written overall, and the results are interesting, if somewhat shallow.

Update: read the author feedback and all reviews and still agree the paper should be accepted. This paper addresses the problem of performing Bayesian inference on mobile hardware (e.g., self-driving car, phone) efficiently. As one would imagine, approaches that operate with discrete values have an advantage in hardware. Variational inference, a method for approximate Bayesian inference, often involves continuous latent variables and continuous variational parameters. This paper's contribution is to cast everything in the discrete space with an approximating discrete prior.