CIF: Small: Collaborative Research: Generative Adversarial Networks: From Art to Science

CIF：小型：协作研究：生成对抗网络：从艺术到科学

基本信息

批准号：
1908291
负责人：
David Tse
金额：
$ 25万
依托单位：
Stanford University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-07-01 至 2023-06-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1908291&HistoricalAwards=false
关键词：
CIF Small Collaborative Research Generative

项目摘要

In the modern era of big data, although the cost of labeling and analyzing a single data sample has been decreasing rapidly, it is usually outpaced by the unrivaled fast growth of dataset size, which makes it particularly timely to design unsupervised learning algorithms that are able to discover meaningful structures of data without extensive human efforts. Recently, Generative Adversarial Networks (GANs) have emerged as a thriving unsupervised machine learning technique that has led to significant advances in various fields such as computer vision, natural language processing, and others. GANs can generate high-quality realistic images based on unlabeled natural images and perform sophisticated tasks such as synthesizing photos from sketches and coloring images. However, there also exist challenges that need timely solutions. The training of GANs has been reportedly observed to be challenging, unstable, and not easily reproducible. This project seeks to conduct a systematic study of GANs through the fundamental formulation, generalization and optimization issues. The transformative potential of the project is in the development of foundational tools and practical guidelines through novel combinations of optimal transport, information theory, convex geometry, and empirical process theory. The goal of this project is four-fold: (1) develop a theoretical framework for analyzing the generalization properties of GANs in high-dimensions; (2) suggest principled approaches to design GANs to achieve optimal statistical properties; (3) diagnose GANs when issues such as mode collapse or discriminator winning occur; (4) develop computationally efficient algorithms that can attain the statistical limits of well-designed GANs. The theory and algorithms developed within this projection will have impact on various engineering and scientific applications and provide insights for the proper usage of GANs in the real world.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在大数据的现代时代，虽然标记和分析单个数据样本的成本一直在迅速下降，但它通常被数据集大小无与伦比的快速增长所超越，这使得设计能够无需大量人类努力即可发现有意义的数据结构。最近，生成对抗网络（GAN）作为一种蓬勃发展的无监督机器学习技术而出现，它在计算机视觉、自然语言处理等各个领域取得了重大进展。 GAN 可以基于未标记的自然图像生成高质量的逼真图像，并执行复杂的任务，例如从草图合成照片和为图像着色。但也存在需要及时解决的挑战。据报道，GAN 的训练具有挑战性、不稳定且不易重现。该项目旨在通过基本的公式化、泛化和优化问题对 GAN 进行系统研究。该项目的变革潜力在于通过最佳传输、信息论、凸几何和经验过程理论的新颖组合来开发基础工具和实用指南。该项目的目标有四个：（1）开发一个理论框架来分析 GAN 在高维上的泛化特性； (2) 提出设计 GAN 的原则性方法，以实现最佳统计特性； (3) 当出现模式崩溃或判别器获胜等问题时诊断 GAN； (4) 开发计算高效的算法，能够达到精心设计的 GAN 的统计极限。该预测中开发的理论和算法将对各种工程和科学应用产生影响，并为现实世界中正确使用 GAN 提供见解。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力评估进行评估，被认为值得支持。优点和更广泛的影响审查标准。