Abstract
Abstract
In this paper, we present a method for explaining the results produced by dynamic programming (DP) algorithms. Our approach is based on retaining a granular representation of values that are aggregated during program execution. The explanations that are created from the granular representations can answer questions of why one result was obtained instead of another and therefore can increase the confidence in the correctness of program results.
Our focus on dynamic programming is motivated by the fact that dynamic programming offers a systematic approach to implementing a large class of optimization algorithms which produce decisions based on aggregated value comparisons. It is those decisions that the granular representation can help explain. Moreover, the fact that dynamic programming can be formalized using semirings supports the creation of a Haskell library for dynamic programming that has two important features. First, it allows programmers to specify programs by recurrence relationships from which efficient implementations are derived automatically. Second, the dynamic programs can be formulated generically (as type classes), which supports the smooth transition from programs that only produce result to programs that can run with granular representation and also produce explanations. Finally, we also demonstrate how to anticipate user questions about program results and how to produce corresponding explanations automatically in advance.
Publisher
Cambridge University Press (CUP)
Reference41 articles.
1. Goal-Directed Debugging of Spreadsheets
2. Debugging Haskell by observing intermediate data structures;Gill;Electron. Notes Theoretical Comput. Sci.,2001
3. Semirings and their Applications
4. Khan, O. Z. , Poupart, P. & Black, J. P. (2009) Minimal sufficient explanations for factored Markov decision processes. In 19th International Conference on Automated Planning and Scheduling, pp. 194–200.
5. Semiring frameworks and algorithms for shortest-distance problems;Mohri;J. Autom. Lang. Comb.,2002
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A framework for inherently interpretable optimization models;European Journal of Operational Research;2023-11
2. A visual notation for succinct program traces;Journal of Computer Languages;2023-06
3. Explainable quantum clustering method to model medical data;Knowledge-Based Systems;2023-05
4. An Interactive Interpreter for Two Dimensional Lucid;IEEE Access;2022
5. MADMAX: a DSL for explanatory decision making;Proceedings of the 20th ACM SIGPLAN International Conference on Generative Programming: Concepts and Experiences;2021-10-17