Alban Desmaison

TL;DR: An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.

TL;DR: PyTorch as discussed by the authors is a machine learning library that provides an imperative and Pythonic programming style that makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs.

TL;DR: This paper details the principles that drove the implementation of PyTorch and how they are reflected in its architecture, and explains how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance.

TL;DR: The authors propose to learn disentangled representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder, which allows to train partially-specified models that make relatively strong assumptions about a subset of interpretable variables and rely on the flexibility of neural networks for the remaining variables.

TL;DR: The authors propose to learn disentangled representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder, which allows to train partially-specified models that make relatively strong assumptions about a subset of interpretable variables and rely on the flexibility of neural networks for the remaining variables.