Accelerator physics relies on numerical algorithms to solve optimization problems in online
accelerator control and tasks such as experimental design and model calibration in …

The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

NumPyro is a lightweight library that provides an alternate NumPy backend to the Pyro
probabilistic programming language with the same modeling interface, language primitives …

Artificial intelligence has recently experienced remarkable advances, fueled by large
models, vast datasets, accelerated hardware, and, last but not least, the transformative …

Prompted models have demonstrated impressive few-shot learning abilities. Repeated
interactions at test-time with a single model, or the composition of multiple models together …

The development and deployment of machine learning systems can be executed easily with
modern tools, but the process is typically rushed and means-to-an-end. Lack of diligence …

Particle Filtering (PF) methods are an established class of procedures for performing
inference in non-linear state-space models. Resampling is a key ingredient of PF necessary …

Treating neural network inputs and outputs as random variables, we characterize the
structure of neural networks that can be used to model data that are invariant or equivariant …

We study the problem of combining neural networks with symbolic reasoning. Recently
introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as …

We show that many machine-learning algorithms are specific instances of a single algorithm
called the Bayesian learning rule. The rule, derived from Bayesian principles, yields a wide …