Making life better one large system at a time: Challenges for UAI research

TL;DR

This paper discusses how UAI research can address the management challenges of complex IT ecosystems by improving algorithms and tools for data-driven decision making in large distributed systems.

Contribution

It highlights the relevance of UAI research to practical challenges in managing complex systems and discusses open problems with real-world examples.

Findings

UAI techniques can improve diagnosis in distributed systems

Model discovery aids in understanding complex IT ecosystems

Policy optimization enhances decision-making processes

Abstract

The rapid growth and diversity in service offerings and the ensuing complexity of information technology ecosystems present numerous management challenges (both operational and strategic). Instrumentation and measurement technology is, by and large, keeping pace with this development and growth. However, the algorithms, tools, and technology required to transform the data into relevant information for decision making are not. The claim in this paper (and the invited talk) is that the line of research conducted in Uncertainty in Artificial Intelligence is very well suited to address the challenges and close this gap. I will support this claim and discuss open problems using recent examples in diagnosis, model discovery, and policy optimization on three real life distributed systems.