Research
We use heuristics all the time across many systems including those that are critical to production services. Production systems use heuristics because they are faster or scale better than their optimal counterparts. But practitioners often don’t know the performance gap between the heuristic and the optimal, or another heuristic in realistic scenarios. We present MetaOpt, a system that helps analyze heuristics.
MetaEase is a framework for automatically finding worst-case inputs of heuristics by maximizing the gap between heuristic and optimal solutions. It combines symbolic execution (KLEE) with gradient-based optimization to efficiently explore the input space. This codebase supports multiple problems: The…
MetaOpt is the first general-purpose and scalable tool that enables users to analyze a broad class of heuristics through easy-to-use abstractions that apply to a broad range of practical heuristics. For more information, checkout MetaOpt’s project webpage and our NSDI’24 paper (Finding Adversarial…