权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Resolving Parametric Misspecification: Joint Schemes for Computation and Learning

解决参数错误指定：计算和学习的联合方案

基本信息

批准号：
1400217
负责人：
Uday Shanbhag
金额：
$ 30万
依托单位：
Pennsylvania State Univ University Park
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2014
资助国家：
美国
起止时间：
2014-08-01 至 2018-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1400217&HistoricalAwards=false
关键词：
Resolving Parametric Misspecification Joint Schemes

项目摘要

The objective of this research is to consider the solution of convex optimization and variational inequality problems complicated by misspecified parameters. A possibly naive sequential approach would first (i) estimate the problem parameters accurately through learning; and then (ii) solve the associated computational problem. Unfortunately, as the learning problems grow in size and complexity, such a framework is hampered by the significant increase in solution time to obtain accurate parameter estimates. Furthermore, any parameter estimation error propagates to the computational problem, possibly with devastating impact. Accordingly, on contrary to the naïve sequential approach, this research will aim to develop gradient-based algorithms that can simultaneously learn the misspecified parameter and solve the computational problem corresponding to the correct parameter. More generally, these coupled schemes will be shown to be capable of contending with problem intricacies such as uncertainty and nonsmoothness. Importantly, this methodology will cope with situations where the observations used in the learning problem may depend on the computational process. The research will emphasize the development of global convergence statements, iteration complexity results, regret bounds with reference to offline algorithms, and trade-offs between exploration and exploitation.If successful, this research will find impact at several levels. At a fundamental level, this research is expected to lead to new truly adaptive algorithms that can both learn parameters and optimize the associated systems simultaneously. The algorithms will make impact through addressing a wide range of large-scale application problems that are complicated by misspecification, including portfolio selection problems and distributed optimization of networked systems. Finally, the educational component of this project will comprise of undergraduate research projects and high school course modules.

这项研究的目的是考虑凸优化和变分不等式问题的解，这些问题由错误指定的参数复杂。一种可能很幼稚的序贯方法将首先(I)通过学习准确地估计问题参数；然后(Ii)解决相关的计算问题。不幸的是，随着学习问题的规模和复杂性的增长，这样的框架受到了显著增加的求解时间的阻碍，以获得准确的参数估计。此外，任何参数估计误差都会传播到计算问题上，可能会产生毁灭性的影响。因此，与朴素的序贯方法相反，本研究的目标是开发基于梯度的算法，该算法可以同时学习错误指定的参数，并解决与正确参数对应的计算问题。更广泛地说，这些耦合方案将被证明能够应对复杂的问题，如不确定性和非平稳性。重要的是，这种方法将处理在学习问题中使用的观察可能取决于计算过程的情况。这项研究将着重于全局收敛语句、迭代复杂性结果、参考离线算法的遗憾界限以及探索和利用之间的权衡。如果成功，这项研究将在多个层面上产生影响。从根本上讲，这项研究有望带来新的真正自适应的算法，既能学习参数，又能同时优化相关系统。这些算法将通过解决因错误说明而复杂的一系列大规模应用问题来产生影响，包括投资组合选择问题和网络系统的分布式优化。最后，该项目的教育部分将由本科生研究项目和高中课程模块组成。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Efficient Optimization Algorithms for Robust Principal Component Analysis and Its Variants

DOI：
10.1109/jproc.2018.2846606
发表时间：
2018-06
期刊：
Proceedings of the IEEE
影响因子：
20.6
作者：
Shiqian Ma;N. Aybat
通讯作者：
Shiqian Ma;N. Aybat

Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus Optimization

DOI：
10.1109/tac.2017.2713046
发表时间：
2018-01-01
期刊：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
影响因子：
6.8
作者：
Aybat, N. S.;Wang, Z.;Ma, S.
通讯作者：
Ma, S.

Multi-agent constrained optimization of a strongly convex function over time-varying directed networks

DOI：
10.1109/allerton.2017.8262781
发表时间：
2017-06
期刊：
2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
影响因子：
0
作者：
E. Y. Hamedani;N. Aybat
通讯作者：
E. Y. Hamedani;N. Aybat

A primal-dual method for conic constrained distributed optimization problems