Convex Smoothed Autoencoder-Optimal Transport model
Not on the map. Why?
Abstract (arXiv)
Generative modelling is a key tool in unsupervised machine learning which has achieved stellar success in recent years. Despite this huge success, even the best generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) come with their own shortcomings, mode collapse and mode mixture being the two most prominent problems. In this paper we develop a new generative model capable of generating samples which resemble the observed data, and is free from mode collapse and mode mixture. Our model is inspired by the recently proposed Autoencoder-Optimal Transport (AE-OT) model and tries to improve on it by addressing the problems faced by the AE-OT model itself, specifically with respect to the sample generation algorithm. Theoretical results concerning the bound on the error in approximating the non-smooth Brenier potential by its smoothed estimate, and approximating the discontinuous optimal transport map by a smoothed optimal transport map estimate have also been established in this paper.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 14 Jan 2021.
Builds on
19 of 45 references.
References · 19
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2014NICE: Non-linear Independent Components Estimationcited by 1,052
- 2019An Introduction to Variational Autoencoderscited by 997
- 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
- 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
- 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
- 2016Variational Lossy Autoencodercited by 175
- 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
- 2016Generative Models and Model Criticism via Optimized Maximum Mean Discrepancycited by 99
7 more
- 2018Geometric Understanding of Deep Learningcited by 41
- 2013Deep Generative Stochastic Networks Trainable by Backpropcited by 36
- 2017A Geometric View of Optimal Transportation and Generative Modelcited by 31
- 2019Quantitative stability of optimal transport maps and linearization of the 2-Wasserstein spacecited by 25
- 2015A Computational Framework for Multivariate Convex Regression and its Variantscited by 16
- 2013Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Formcited by 5
- 2019Mode Collapse and Regularity of Optimal Transportation Mapscited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.