Document Type

Dissertation

Date of Award

8-31-2022

Degree Name

Doctor of Philosophy in Computing Sciences - (Ph.D.)

Department

Computer Science

First Advisor

Jing Li

Second Advisor

Marvin K. Nakayama

Third Advisor

James M. Calvin

Fourth Advisor

Pan Xu

Fifth Advisor

Wenge Guo

Abstract

Many application areas employ various risk measures, such as a quantile, to assess risks. For example, in finance, risk managers employ a quantile to help determine appropriate levels of capital needed to be able to absorb (with high probability) large unexpected losses in credit portfolios comprising loans, bonds, and other financial instruments subject to default. This dissertation discusses the computation of risk measures in finance and parallel real-time scheduling.

Firstly, two estimation approaches are compared for one risk measure, a quantile, via randomized quasi-Monte Carlo (RQMC) in an asymptotic setting where the number of randomizations for RQMC grows large, but the size of the low-discrepancy point set remains fixed. In the first method, for each randomization, it computes an estimator of the cumulative distribution function (CDF), which is inverted to obtain a quantile estimator, and the overall quantile estimator is the sample average of the quantile estimators across randomizations. The second approach instead computes a single quantile estimator by inverting one CDF estimator across all randomizations. Because quantile estimators are generally biased, the first method leads to an estimator that does not converge to the true quantile as the number of randomizations goes to infinity. In contrast, the second estimator does, and a central limit theorem is established for it. To get an improvement, we use conditional Monte Carlo (CMC) to obtain a smoother estimate of the distribution function, and we combine this with the second RQMC to further reduce the variance. The result is a much more accurate quantile estimator, whose mean square error can converge even faster than the canonical rate of O(1/n).

Secondly, another risk measure is estimated, namely economic capital (EC), which is defined as the difference between a quantile and the mean of the loss distribution, given a stochastic model for a portfolio’s loss over a given time horizon. This work applies measure-specific importance sampling to separately estimate the two components of the EC, which can lead to a much smaller variance than when estimating both terms simultaneously.

Finally, for parallel real-time tasks, the federated scheduling paradigm, which assigns each parallel task a set of dedicated cores, achieves good theoretical bounds by ensuring exclusive use of processing resources to reduce interferences. However, because cores share the last-level cache and memory bandwidth resources, in practice tasks may still interfere with each other despite executing on dedicated cores. To tackle this issue, this work presents a holistic resource allocation framework for parallel real-time tasks under federated scheduling. Under the proposed framework, in addition to dedicated cores, each parallel task is also assigned with dedicated cache and memory bandwidth resources. This work also shows the study of the characteristics of parallel tasks upon different resource allocations following a measurement-based approach and proposes a technique to handle the challenge of tremendous profiling for all resource allocation combinations under this approach. Further, it proposes a holistic resource allocation algorithm that well balances the allocation between different resources to achieve good schedulability. Additionally, this work provides a full implementation of the framework by extending the federated scheduling system with Intel’s Cache Allocation Technology and MemGuard. It also demonstrates the practicality of the proposed framework via extensive numerical evaluations and empirical experiments using real benchmark programs. In the end, the discussion about the application of risk measures for real-time scheduling is given for future work.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.