Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 8881-8891, 2019.
EI
Keywords:
Abstract:
Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure ("Structured Procrastination") that provably achieves near optimal performance with high probability and with nearly minimal runtime in th...More
Code:
Data:
Full Text
Tags
Comments