March 25, 2024, 4:42 a.m. | Lea Kunkel, Mathias Trabs

cs.LG updates on arXiv.org arxiv.org

arXiv:2403.15312v1 Announce Type: cross
Abstract: The empirical success of Generative Adversarial Networks (GANs) caused an increasing interest in theoretical research. The statistical literature is mainly focused on Wasserstein GANs and generalizations thereof, which especially allow for good dimension reduction properties. Statistical results for Vanilla GANs, the original optimization problem, are still rather limited and require assumptions such as smooth activation functions and equal dimensions of the latent space and the ambient space. To bridge this gap, we draw a connection …

abstract adversarial arxiv cs.lg gans generative generative adversarial networks good literature math.st networks optimization perspective research results statistical stat.ml stat.th success type

Senior Machine Learning Engineer

@ GPTZero | Toronto, Canada

ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)

@ HelloBetter | Remote

Doctoral Researcher (m/f/div) in Automated Processing of Bioimages

@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena

Director, Global Success Business Intelligence

@ Salesforce | Texas - Austin

Deep Learning Compiler Engineer - MLIR

@ NVIDIA | US, CA, Santa Clara

Commerce Data Engineer (Remote)

@ CrowdStrike | USA TX Remote