RI: AF: Small: Optimizing probabilities for learning: sampling meets optimization

RI：AF：小：优化学习概率：采样满足优化

基本信息

批准号：
1909365
负责人：
Peter Bartlett
金额：
$ 45万
依托单位：
University of California-Berkeley
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-08-01 至 2023-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1909365&HistoricalAwards=false
关键词：
RI AF Small Optimizing probabilities

项目摘要

Methods for large-scale machine learning and artificial intelligence (AI) have had major impacts on the world over the past decade, including in both industrial and scientific contexts. These spectacular successes are driven by a combination of the availability of massive datasets, and appropriate models and algorithms for extracting useful information and insights from these datasets. This research project aims to advance the methodology and understanding of algorithms for large-scale machine learning and AI by exploiting the interplay between sampling and optimization. In particular, two grand challenges are addressed: first, the tools and insights of optimization theory can develop more effective design and analysis techniques for sampling methods; second, these techniques can be used to design and analyze optimization methods for problems such as those that arise in deep learning. Successful research outcomes of this project are likely to increase the understanding of methods used for sampling and for optimization, and to facilitate their principled design. Successful outcomes have a significant potential for practical impact in the large and growing set of applications where large-scale sampling and optimization methods are used, including computer vision, speech recognition, and self-driving cars. The research will support the development of graduate students, will be disseminated through large graduate courses at Berkeley and their web-based course materials, and has the potential to benefit the broader community through the application of the methods studied in deployed AI systems.The project has three main technical directions. First, it aims to identify the inherent difficulty of sampling problems by proving lower bounds. Second, it aims to produce analysis tools and design methodologies for sampling algorithms based on a certain family of stochastic differential equations known as a Langevin diffusion. This will enable the development of sampling algorithms with performance guarantees. Third, it will use the viewpoint of sampling techniques to analyze and design stochastic gradient methods for nonconvex optimization problems, such as the optimization of parameters in deep neural networks. An additional outcome of the project will be the organization of a workshop on the topic of the interface between sampling and optimization.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.

过去十年，大规模机器学习和人工智能 (AI) 方法对世界产生了重大影响，包括在工业和科学领域。这些惊人的成功是由海量数据集的可用性以及从这些数据集中提取有用信息和见解的适当模型和算法相结合推动的。该研究项目旨在通过利用采样和优化之间的相互作用来推进大规模机器学习和人工智能算法的方法论和理解。特别是，解决了两个重大挑战：首先，优化理论的工具和见解可以为采样方法开发更有效的设计和分析技术；其次，这些技术可用于设计和分析深度学习中出现的问题的优化方法。该项目的成功研究成果可能会增加对采样和优化方法的理解，并促进其原则设计。成功的成果对于使用大规模采样和优化方法的大量且不断增长的应用（包括计算机视觉、语音识别和自动驾驶汽车）具有巨大的实际影响潜力。该研究将支持研究生的发展，将通过伯克利的大型研究生课程及其基于网络的课程材料进行传播，并有可能通过在已部署的人工智能系统中研究的方法的应用来造福更广泛的社区。该项目拥有三个主要技术方向。首先，它的目的是通过证明下界来确定抽样问题的固有难度。其次，它的目标是为基于称为朗之万扩散的随机微分方程组的采样算法提供分析工具和设计方法。这将使开发具有性能保证的采样算法成为可能。第三，从采样技术的角度来分析和设计非凸优化问题的随机梯度方法，例如深度神经网络中参数的优化。该项目的另一个成果将是组织一次关于采样和优化之间的接口主题的研讨会。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值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

期刊论文数量（10）

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 Approximate Thompson Sampling with Langevin Algorithms

基于 Langevin 算法的近似 Thompson 采样

DOI：
10.6028/nist.sp.800-142
发表时间：
2024-09-13
期刊：
INTERSPEECH 2023
影响因子：
0
作者：
Eric V. Mazumdar;Aldo Pacchiano;Yi;Michael I. Jordan;P. Bartlett
通讯作者：
P. Bartlett

Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity

改进朗之万扩散离散化的界限：无凸性的接近最优速率

DOI：
10.3150/21-bej1343
发表时间：
2019-07-25
期刊：
Bernoulli
影响因子：
1.5
作者：
Wenlong Mou;Nicolas Flammarion;M. Wainwright;P. Bartlett
通讯作者：
P. Bartlett

Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning

使用线性架构稳定 Q 学习，实现可证明高效的学习

DOI：
10.48550/arxiv.2206.00796
发表时间：
2022-06-01
期刊：
影响因子：
0
作者：
A. Zanette;M. Wainwright
通讯作者：
M. Wainwright

High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm

高阶 Langevin 扩散产生加速 MCMC 算法

DOI：
10.1073/pnas.1820003116
发表时间：
2019-08-28
期刊：
ArXiv
影响因子：
0
作者：
Wenlong Mou;Yian Ma;Yi;M. Wainwright;P. Bartlett;Michael I. Jordan
通讯作者：
Michael I. Jordan

Langevin Monte Carlo without smoothness

没有平滑度的朗之万蒙特卡罗

DOI：
发表时间：
2020-08
期刊：
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics
影响因子：
0
作者：
Chatterji, Niladri;Diakonikolas, Jelena;Jordan, Michael I.;Bartlett, Peter L.
通讯作者：
Bartlett, Peter L.