CAREER: Scaling Up Knowledge Discovery in High-Dimensional Data Via Nonconvex Statistical Optimization

职业：通过非凸统计优化扩大高维数据中的知识发现

基本信息

批准号：
1906169
负责人：
Quanquan Gu
金额：
$ 50.6万
依托单位：
University of California-Los Angeles
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2018
资助国家：
美国
起止时间：
2018-07-01 至 2024-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1906169&HistoricalAwards=false
关键词：
CAREER Scaling Up Knowledge Discovery

项目摘要

The past decade has witnessed a surge of research activities on knowledge discovery in high-dimensional data, among which convex optimization-based methods are widely used. While convex optimization algorithms enjoy global convergence guarantees, they are not always scalable to high-dimensional massive data. Motivated by the empirical success of nonconvex methods such as matrix factorization, the objective of this project is to develop a new generation of principled nonconvex statistical optimization algorithms to scale up high-dimensional machine learning methods. This project amplifies the utility of high-dimensional knowledge discovery methods in various fields such as computational genomics and recommendation systems. It incorporates the resulting research outcomes into curriculum development and online courses, to train a new generation of machine learning and data mining practitioners. In addition, special training is provided to K-12 students and community college students for a broader education of modern data analysis techniques.This project consists of three synergistic research thrusts. First, it develops a family of nonconvex algorithms for structured sparse learning, including extensions to both parallel computing and distributed computing. Second, it devises a unified nonconvex optimization framework for low-rank matrix estimation, which covers a wide range of low-rank matrix learning problems such as matrix completion and preference learning. Several acceleration techniques are also explored. Third, it develops a family of alternating optimization algorithms, to solve the bi-convex optimization problem for estimating various complex statistical models. This project integrates modern optimization techniques with model-based statistical thinking, and provides a systematic way to design nonconvex high-dimensional machine learning methods with strong theoretical guarantees. The targeted applications include but not limited to computational genomics, neuroscience, and recommendation systems.

过去十年，高维数据知识发现的研究活动激增，其中基于凸优化的方法被广泛使用。虽然凸优化算法享有全局收敛保证，但它们并不总是可扩展到高维海量数据。受矩阵分解等非凸方法经验成功的推动，该项目的目标是开发新一代有原则的非凸统计优化算法，以扩展高维机器学习方法。该项目扩大了高维知识发现方法在计算基因组学和推荐系统等各个领域的效用。它将研究成果纳入课程开发和在线课程中，以培训新一代机器学习和数据挖掘从业者。此外，还为 K-12 学生和社区学院学生提供特殊培训，以进行更广泛的现代数据分析技术教育。该项目由三个协同研究重点组成。首先，它开发了一系列用于结构化稀疏学习的非凸算法，包括并行计算和分布式计算的扩展。其次，它为低秩矩阵估计设计了一个统一的非凸优化框架，涵盖了广泛的低秩矩阵学习问题，例如矩阵补全和偏好学习。还探索了几种加速技术。第三，它开发了一系列交替优化算法，以解决估计各种复杂统计模型的双凸优化问题。该项目将现代优化技术与基于模型的统计思维相结合，为设计非凸高维机器学习方法提供了系统的途径，并具有强有力的理论保证。目标应用包括但不限于计算基因组学、神经科学和推荐系统。

项目成果

期刊论文数量（81）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits

关于线性上下文老虎机中错误指定和次优差距之间的相互作用

DOI：
10.48550/arxiv.2303.09390
发表时间：
2023-03-16
期刊：
ArXiv
影响因子：
0
作者：
Weitong Zhang;Jiafan He;Zhiyuan Fan;Q. Gu
通讯作者：
Q. Gu

Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation

线性函数逼近强化学习的统一 PAC 界限

DOI：
发表时间：
2021-01
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
He, Jiafan;Zhou, Dongruo;Gu, Quanquan
通讯作者：
Gu, Quanquan

Learning One-hidden-layer ReLU Networks via Gradient Descent

通过梯度下降学习单隐藏层 ReLU 网络

DOI：
发表时间：
2019-01
期刊：
Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS
影响因子：
0
作者：
Zhang, Xiao;Yu, Yaodong;Wang, Lingxiao;Gu, Quanquan
通讯作者：
Gu, Quanquan

Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping

通过特征映射为折扣 MDP 提供可证明有效的强化学习