FRG: Collaborative Research: Robust, Efficient, and Private Deep Learning Algorithms

FRG：协作研究：稳健、高效、私密的深度学习算法

• 批准号: 1952644
• 负责人: Jack Xin
• 金额: $ 14.02万
• 依托单位: University of California-Irvine
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-15 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1952644&HistoricalAwards=false
• 关键词: FRG; Collaborative; Research; Robust; Efficient

This project develops robust, accurate, and efficient next-generation deep learning algorithms with data privacy and theoretical guarantees for solving challenging artificial intelligence (AI) problems. The methods will have robustness to adversarial attacks with theoretical guarantees. The project will push artificial intelligence gains in performance and privacy to mobile devices. A broad range of applications includes autonomous driving, drug and material discovery, medical treatment planning, national defense, privacy-preserving machine learning at the edge, federated learning, and also blockchain. Moreover, the developed tools will significantly scale the existing scientific simulations to ultra-large scale and high-dimensional scenarios. This project will partially support one graduate student per year at each campus.Our approach toward trustworthy deep learning is theoretically principled by modern partial differential equations and optimization algorithms and theories. The project involves new algorithmic and theoretical techniques to tackle graph representation in high-dimensional non-convex, non-smooth AI settings. In particular, the project will study (1) developing adversarial robust deep learning algorithms and their theoretical foundations; (2) improving the accuracy of deep learning leveraging new stochastic optimization and principled neural network unit design assisted neural architecture search; (3) advancing deep neural networks compression with algorithms and hardware co-design; (4) designing new data privacy mechanisms to optimally tradeoff between utility and privacy; (5) inventing new quantitative analysis tools to decipher the mysteries of deep learning theoretical challenges; (6) quantifying uncertainties of sophisticated deep learning algorithms. The project trains a diverse body of graduate and undergraduate students at UC Irvine, UCLA, and University of Utah through collaborative education and research activities in applied mathematics, computer science, data science, and general biological, physical, and sociological disciplines.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.

该项目开发稳健、准确和高效的下一代深度学习算法，具有数据隐私和解决具有挑战性的人工智能(AI)问题的理论保证。该方法在理论上保证了对敌意攻击的稳健性。该项目将把人工智能在性能和隐私方面的进步推广到移动设备上。广泛的应用包括自动驾驶、药物和材料发现、医疗规划、国防、边缘隐私保护机器学习、联邦学习，以及区块链。此外，开发的工具将极大地将现有的科学模拟扩展到超大规模和高维场景。这个项目将部分支持每个校区每年一名研究生。我们对值得信赖的深度学习的方法是以现代偏微分方程组和优化算法和理论为理论基础的。该项目涉及新的算法和理论技术，以解决高维非凸、非光滑人工智能环境中的图形表示。特别是，该项目将研究(1)开发对抗性稳健的深度学习算法及其理论基础；(2)利用新的随机优化和原则性神经网络单元设计辅助神经体系结构搜索来提高深度学习的准确性；(3)通过算法和硬件共同设计来推进深度神经网络压缩；(4)设计新的数据隐私机制，以优化效用和隐私之间的权衡；(5)发明新的量化分析工具，以破解深度学习理论挑战的奥秘；(6)量化复杂深度学习算法的不确定性。该项目通过合作教育和研究活动，在加州大学欧文分校、加州大学洛杉矶分校和犹他大学培养了一批不同的研究生和本科生。该奖项反映了NSF的法定使命，通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Lorentzian peak sharpening and sparse blind source separation for NMR spectroscopy

• DOI: 10.1007/s11760-021-02002-4
• 发表时间: 2020-09
• 期刊: Signal, Image and Video Processing
• 作者: Yuanchang Sun;J. Xin

Synchronized Front Propagation and Delayed Flame Quenching in Strain G-Equation and Time-Periodic Cellular Flows

应变 G 方程和时间周期细胞流中的同步前沿传播和延迟火焰淬火

• 发表时间: 2023
• 期刊: Minimax theory and its applications
• 影响因子: 0.7
• 作者: Liu, Yu-Yu;Xin, Jack
• 通讯作者: Xin, Jack

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data

• DOI: 10.1109/access.2023.3297890
• 发表时间: 2023-02
• 期刊: IEEE Access
• 影响因子: 3.9
• 作者: Zhijian Li;Biao Yang;Penghang Yin;Y. Qi;J. Xin

Structured Sparsity of Convolutional Neural Networks via Nonconvex Sparse Group Regularization

• DOI: 10.3389/fams.2020.529564
• 发表时间: 2021-02
• 作者: Kevin Bui;Fredrick Park;Shuai Zhang;Y. Qi;J. Xin

Convergence of Hyperbolic Neural Networks Under Riemannian Stochastic Gradient Descent

黎曼随机梯度下降下双曲神经网络的收敛性

• DOI: 10.1007/s42967-023-00302-9
• 发表时间: 2023
• 期刊: Communications on Applied Mathematics and Computation
• 影响因子: 1.6
• 作者: Whiting, Wes;Wang, Bao;Xin, Jack
• 通讯作者: Xin, Jack