Resolving Parametric Misspecification: Joint Schemes for Computation and Learning
Resolving Parametric Misspecification: Joint Schemes for Computation and Learning
批准号:
1400217
负责人:
Uday Shanbhag
金额:
$30.0万
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
项目状态:
已结题
起止时间:
2014-08-01 至 2018-07-31
中文摘要
点击翻译按钮获取中文摘要
英文摘要
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.
期刊论文(7)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
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
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.
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:
--
作者:
[E. Y. Hamedani;N. Aybat]
通讯作者:
E. Y. Hamedani;N. Aybat
DOI:
--
发表时间:
2016-07
期刊:
影响因子:
--
作者:
[N. Aybat;E. Y. Hamedani]
通讯作者:
N. Aybat;E. Y. Hamedani
DOI:
10.1109/acssc.2016.7869152
发表时间:
2016-11
期刊:
2016 50th Asilomar Conference on Signals, Systems and Computers
影响因子:
--
作者:
[N. Aybat;E. Y. Hamedani]
通讯作者:
N. Aybat;E. Y. Hamedani
共 7 条
6th INFORMS Simulation Society Research Workshop; University Park, Pennsylvania; June 22-24, 2020
-
批准号:1939336
-
项目类别:Standard Grant
-
资助金额:$1.0万
-
财政年份:2020
-
负责人:Uday Shanbhag
-
依托单位:
Collaborative Research: Nash Equilibrium Problems under Uncertainty
-
批准号:1538193
-
项目类别:Standard Grant
-
资助金额:$11.0万
-
财政年份:2015
-
负责人:Uday Shanbhag
-
依托单位:
COLLABORATIVE RESEARCH: Commitment, Expansion, and Pricing in Uncertain Power Markets: Discrete Hierarchical Models and Scalable Algorithms
-
批准号:1408366
-
项目类别:Standard Grant
-
资助金额:$21.0万
-
财政年份:2014
-
负责人:Uday Shanbhag
-
依托单位:
CAREER: Stochastic and Robust Variational Inequality Problems: Analysis, Computation and Applications to Power Markets
-
批准号:1246887
-
项目类别:Standard Grant
-
资助金额:$40.0万
-
财政年份:2012
-
负责人:Uday Shanbhag
-
依托单位:
CAREER: Stochastic and Robust Variational Inequality Problems: Analysis, Computation and Applications to Power Markets
-
批准号:1151138
-
项目类别:Standard Grant
-
资助金额:$40.0万
-
财政年份:2012
-
负责人:Uday Shanbhag
-
依托单位:
Addressing Competition, Dynamics and Uncertainty in Optimization Problems: Theory, Algorithms, Applications and Grid-Computing Extensions
-
批准号:0728863
-
项目类别:Standard Grant
-
资助金额:$20.0万
-
财政年份:2007
-
负责人:Uday Shanbhag
-
依托单位:
海外基金