Detecting and Understanding Real-World Differential Performance Bugs in Machine Learning Libraries

no code implementations • 3 Jun 2020 • Saeid Tizpaz-Niari, Pavol Cerný, Ashutosh Trivedi

On a set of micro-benchmarks, we show that our approach outperforms state-of-the-art fuzzers in finding inputs to characterize the differential performance.

BIG-bench Machine Learning Clustering