Federated learning (FL) preserves data privacy by exchanging gradients instead of local
training data. However, these private data can still be reconstructed from the exchanged …

In view of training increasingly complex learning architectures, we establish a nonsmooth
implicit function theorem with an operational calculus. Our result applies to most practical …

Automatic differentiation, as implemented today, does not have a simple mathematical
model adapted to the needs of modern machine learning. In this work we articulate the …

Automatic differentiation is a popular technique for computing derivatives of computer
programs. While automatic differentiation has been successfully used in countless …

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 …

We study the correctness of automatic differentiation (AD) in the context of a higher-order,
Turing-complete language (PCF with real numbers), both in forward and reverse mode. Our …

Emerging research in computer graphics, inverse problems, and machine learning requires
us to differentiate and optimize parametric discontinuities. These discontinuities appear in …

Differentiation along algorithms, ie, piggyback propagation of derivatives, is now routinely
used to differentiate iterative solvers in differentiable programming. Asymptotics is well …

The relational data model was designed to facilitate large-scale data management and
analytics. We consider the problem of how to differentiate computations expressed …

This paper introduces SMCP3, a method for automatically implementing custom sequential
Monte Carlo samplers for inference in probabilistic programs. Unlike particle filters and …