Semantic Scholar Open Access 2021 134 sitasi

A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning

Iris A. M. Huijben W. Kool Max B. Paulus Ruud J. G. van Sloun

Lihat Sumber DOI

Abstrak

The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to facilitate, e.g., drawing multiple samples, sampling from structured domains, or gradient estimation for error backpropagation in neural network optimization. The goal of this survey article is to present background about the Gumbel-max trick, and to provide a structured overview of its extensions to ease algorithm selection. Moreover, it presents a comprehensive outline of (machine learning) literature in which Gumbel-based algorithms have been leveraged, reviews commonly-made design choices, and sketches a future perspective.

Topik & Kata Kunci

Computer Science Mathematics Medicine

Penulis (4)

Iris A. M. Huijben

W. Kool

Max B. Paulus

Ruud J. G. van Sloun

Format Sitasi

APA MLA BibTeX

Huijben, I.A.M., Kool, W., Paulus, M.B., Sloun, R.J.G.v. (2021). A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning. https://doi.org/10.1109/TPAMI.2022.3157042

Akses Cepat

Lihat di Sumber doi.org/10.1109/TPAMI.2022.3157042

Informasi Jurnal

Tahun Terbit: 2021
Bahasa: en
Total Sitasi: 134×
Sumber Database: Semantic Scholar
DOI: 10.1109/TPAMI.2022.3157042
Akses: Open Access ✓