Prescott and Baker (2020) propose a multi-fidelity approach to ABC. In our work, the Russian roulette estimator is used to construct an unbiased, low-fidelity likelihood.

When applied to recordings from the mouse olfactory bulb, our approach reveals low-dimensional population dynamics that are odor specific and have consistent structure across animals.

In this paper, we rely on a broader view of proper composite losses and a recent construct from information geometry, source functions, whose fitting alleviates constraints faced by canonical links.

Despite their successes, modern neural networks (NNs) still suffer from several shortcomings that limit their applicability in some settings.

Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges.

We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs).

V ariational methods are extremely popular in the analysis of network data.