CIF: Small: Collaborative Research: Acceleration Algorithms for Large-scale Nonconvex Optimization

CIF：小型：协作研究：大规模非凸优化的加速算法

• 批准号: 1909291
• 负责人: Yingbin Liang
• 金额: $ 25万
• 依托单位: Ohio State 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: 2019-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1909291&HistoricalAwards=false
• 关键词: CIF; Small; Collaborative; Research; Acceleration

Non-convex optimization problems are ubiquitous in data science, machine learning and artificial intelligence. Non-convexity, together with the high dimension of the model parameters and the large volume of uncertain data, presents significant challenges for solving these problems. Although popular methods have been proposed to speed up optimization algorithms for solving practical large-scale problems, these algorithms do not necessarily converge for non-convex problems, and some of them do not even converge in the convex setting. The primary goal of this project is to develop principled approaches for designing acceleration algorithms with provable theoretical convergence guarantees and superior practical performance for large-scale non-convex optimization. The developed algorithms will be applicable to big data problems in various domains, including deep learning, computer vision, medical image processing, social network learning, etc.This project will design novel, fast, and scalable acceleration algorithms for solving a variety of large-scale non-convex problems including constrained, composite, and saddle point optimization problems. This will include the development of both novel direct acceleration methods inspired by Nesterov's approach, and of indirect acceleration methods via proximal point methods for different types of problems. The performance of these acceleration methods will be explored when combined with randomization methods in order to enhance their scalability with data dimension and volume. Comprehensive numerical validations will be conducted for application problems arising in large-scale data analysis. This project will contribute to a synthesis of optimization with data science, and will be incorporated into curriculum development, and in the training of students and future big data researchers and practitioners.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.

非凸优化问题在数据科学、机器学习和人工智能中普遍存在。非凸性以及模型参数的高维度和大量的不确定数据给解决这些问题带来了巨大的挑战。尽管已经提出了流行的方法来加速解决实际大规模问题的优化算法，但这些算法对于非凸问题不一定收敛，其中一些算法甚至在凸设置中不收敛。该项目的主要目标是开发设计加速算法的原则方法，具有可证明的理论收敛保证和大规模非凸优化的卓越实践性能。所开发的算法将适用于各个领域的大数据问题，包括深度学习、计算机视觉、医学图像处理、社交网络学习等。该项目将设计新颖、快速且可扩展的加速算法，用于解决各种大型数据问题。缩放非凸问题，包括约束、复合和鞍点优化问题。这将包括开发受 Nesterov 方法启发的新型直接加速方法，以及针对不同类型问题的通过近点法的间接加速方法。当与随机化方法相结合时，将探索这些加速方法的性能，以增强其数据维度和数量的可扩展性。针对大规模数据分析中出现的应用问题进行全面的数值验证。该项目将有助于优化与数据科学的综合，并将纳入课程开发以及对学生和未来大数据研究人员和从业者的培训。该奖项反映了 NSF 的法定使命，经评估认为值得支持利用基金会的智力优势和更广泛的影响审查标准。

项目成果

When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence

• 发表时间: 2020-06
• 作者: Ziwei Guan;Tengyu Xu;Yingbin Liang

Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent

• DOI: 10.24963/ijcai.2020/422
• 发表时间: 2020-07
• 作者: Chuhan Wu;Fangzhao Wu;Tao Qi;Yongfeng Huang

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

• 发表时间: 2020-04
• 期刊: arXiv: Learning
• 作者: Tengyu Xu;Zhe Wang-;Yingbin Liang

CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee

• 发表时间: 2020-11
• 作者: Tengyu Xu;Yingbin Liang;Guanghui Lan

Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization

• DOI: 10.24963/ijcai.2020/201
• 发表时间: 2020-02
• 期刊: ArXiv
• 作者: Yi Zhou;Zhe Wang-;Kaiyi Ji;Yingbin Liang;V. Tarokh