The elements of differentiable programming

M Blondel, V Roulet - arxiv preprint arxiv:2403.14606, 2024‏ - arxiv.org
Artificial intelligence has recently experienced remarkable advances, fueled by large
models, vast datasets, accelerated hardware, and, last but not least, the transformative …

A-nesi: A scalable approximate method for probabilistic neurosymbolic inference

E van Krieken, T Thanapalasingam… - Advances in …, 2023‏ - proceedings.neurips.cc
We study the problem of combining neural networks with symbolic reasoning. Recently
introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as …

Automatic differentiation of programs with discrete randomness

G Arya, M Schauer, F Schäfer… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Automatic differentiation (AD), a technique for constructing new programs which compute
the derivative of an original program, has become ubiquitous throughout scientific …

ADEV: Sound automatic differentiation of expected values of probabilistic programs

AK Lew, M Huot, S Staton, VK Mansinghka - Proceedings of the ACM on …, 2023‏ - dl.acm.org
Optimizing the expected values of probabilistic processes is a central problem in computer
science and its applications, arising in fields ranging from artificial intelligence to operations …

Sparse graph learning from spatiotemporal time series

A Cini, D Zambon, C Alippi - Journal of Machine Learning Research, 2023‏ - jmlr.org
Outstanding achievements of graph neural networks for spatiotemporal time series analysis
show that relational constraints introduce an effective inductive bias into neural forecasting …

Auto-differentiation of relational computations for very large scale machine learning

Y Tang, Z Ding, D Jankov, B Yuan… - International …, 2023‏ - proceedings.mlr.press
The relational data model was designed to facilitate large-scale data management and
analytics. We consider the problem of how to differentiate computations expressed …

Branches of a tree: Taking derivatives of programs with discrete and branching randomness in high energy physics

M Kagan, L Heinrich - arxiv preprint arxiv:2308.16680, 2023‏ - arxiv.org
We propose to apply several gradient estimation techniques to enable the differentiation of
programs with discrete randomness in High Energy Physics. Such programs are common in …

Probabilistic programming with programmable variational inference

MCR Becker, AK Lew, X Wang, M Ghavami… - Proceedings of the …, 2024‏ - dl.acm.org
Compared to the wide array of advanced Monte Carlo methods supported by modern
probabilistic programming languages (PPLs), PPL support for variational inference (VI) is …

Discovering dynamics and parameters of nonlinear oscillatory and chaotic systems from partial observations

G Stepaniants, AD Hastewell, DJ Skinner, JF Totz… - Physical Review …, 2024‏ - APS
Despite rapid progress in data acquisition techniques, many complex physical, chemical,
and biological systems remain only partially observable, thus posing the challenge to …

Differentiating Metropolis-Hastings to optimize intractable densities

G Arya, R Seyer, F Schäfer, K Chandra, AK Lew… - arxiv preprint arxiv …, 2023‏ - arxiv.org
We develop an algorithm for automatic differentiation of Metropolis-Hastings samplers,
allowing us to differentiate through probabilistic inference, even if the model has discrete …