CAREER: Information-Theoretic and Statistical Foundations of Generative Models

职业：生成模型的信息理论和统计基础

基本信息

批准号：
1942230
负责人：
Soheil Feizi
金额：
$ 58.97万
依托单位：
University of Maryland, College Park
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2020
资助国家：
美国
起止时间：
2020-03-01 至 2025-02-28
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1942230&HistoricalAwards=false
关键词：
CAREER Information Theoretic Statistical Foundations

项目摘要

Generative machine learning models provide a statistical understanding of data and play an important role in the success of modern machine learning in various application domains including vision, speech, natural languages, and computational biology, among others. Building on the success of deep learning, recent advances in modern generative models hold great promise in revolutionizing various learning methods. Despite this progress, the understanding of some fundamental aspects of these models, required for characterizing their performance guarantees, is still in its infancy. This project aims to elucidate statistical and computational properties of modern generative models by leveraging tools and concepts from information theory, statistics and optimization. This project also includes a comprehensive plan to integrate the research results into an inclusive, diverse and cross-disciplinary educational program at the high school, undergraduate and graduate levels. The overall goal of the research program is to develop a comprehensive and fundamental understanding of the intertwined statistical and computational aspects of modern generative models such as Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs). This project aims to make critical advances in proper formulations of generative models for high dimensional distributions, characterizing statistical limits of these models, and developing efficient computational approaches for solving optimization problems involved during their training. This cross-disciplinary project broadens the scope of the prior knowledge on the interplay between information theory and machine learning and creates a tightly connected loop between theory, algorithms and applications in data science.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.

生成机器学习模型提供了对数据的统计理解，并在现代机器学习在视觉、语音、自然语言和计算生物学等各种应用领域的成功中发挥着重要作用。在深度学习成功的基础上，现代生成模型的最新进展有望彻底改变各种学习方法。尽管取得了这些进展，但对这些模型的一些基本方面的理解（描述其性能保证所需的）仍处于起步阶段。该项目旨在通过利用信息论、统计学和优化的工具和概念来阐明现代生成模型的统计和计算特性。该项目还包括一项综合计划，将研究成果整合到高中、本科生和研究生层次的包容性、多元化和跨学科的教育计划中。该研究项目的总体目标是对现代生成模型（例如生成对抗网络（GAN）和变分自动编码器（VAE））相互交织的统计和计算方面形成全面和基本的理解。该项目旨在在高维分布的生成模型的正确表述、表征这些模型的统计限制以及开发有效的计算方法来解决训练期间涉及的优化问题方面取得关键进展。这个跨学科项目拓宽了关于信息论和机器学习之间相互作用的先验知识的范围，并在数据科学的理论、算法和应用之间创建了紧密连接的循环。该奖项反映了 NSF 的法定使命，并被认为值得支持通过使用基金会的智力优点和更广泛的影响审查标准进行评估。