Fetching the paper…

Reading the bibliography…

2021

Turbo-Sim: a generalised generative model with a physical latent space

Quétant, Guillaume, Drozdova, Mariia, Kinakh, Vitaliy et al.

Original
PDF
Post on X

Understand

We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model.

By maximising the mutual information between the input and the output of both the encoder and the decoder, we are able to rediscover the loss terms usually found in adversarial autoencoders and generative adversarial networks, as well as various more sophisticated related models.
Our generalised framework makes these models mathematically interpretable and allows for a diversity of new ones by setting the weight of each loss term separately.
The framework is also independent of the intrinsic architecture of the encoder and the decoder thus leaving a wide choice for the building blocks of the whole network.

Turbo-Sim: a generalised generative model with a physical latent space · Around

Built on

“Information bottleneck through variational glasses”, 2019
Original
Slava Voloshynovskiy et al · 1912
Earlier work this paper cites.
“Geant4—a simulation toolkit”
S. Agostinelli et al · 2003
Earlier work this paper cites.
“Generative Adversarial Networks”, 2014
Original
Ian. Goodfellow et al · 2014
Earlier work this paper cites.
“The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations”
J. Alwall et al · 2014
Earlier work this paper cites.
“DELPHES 3: a modular framework for fast simulation of a generic collider experiment”
J. de Favereau et al · 2014
Earlier work this paper cites.

Similar

“Adversarial autoencoders”, 2015
Original
Alireza Makhzani et al · 2015
Cited alongside, same era.
“Deep generative models for fast shower simulation in ATLAS”, 2018
ATLAS Collaboration · 2018
Cited alongside, same era.
“Variational Information Bottleneck for Semi-Supervised Classification”
Slava Voloshynovskiy et al · 2020
Cited alongside, same era.
“Fast simulation of the ATLAS calorimeter system with Generative Adversarial Networks”, 2020
ATLAS Collaboration · 2020
Cited alongside, same era.

Then

“AtlFast3: the next generation of fast simulation in ATLAS”, 2021
Original
ATLAS Collaboration · 2021
Closest in time.
“Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed”
Erik Buhmann et al · 2021
Closest in time.
“Foundations of a Fast, Data-Driven, Machine-Learned Simulator”, 2021
Original
Jessica. Howard, Stephan Mandt, Daniel Whiteson and Yibo Yang · 2021
Closest in time.
“EigenGAN: Layer-Wise Eigen-Learning for GANs”, 2021
Original
Zhenliang He, Meina Kan and Shiguang Shan · 2021
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…