Noisy predictions only marginally better than random guessing suffice to provably reduce the search space in exact exponential algorithms for subset selection problems, with runtime speedup scaling smoothly with prediction quality under pairwise independence or no accuracy knowledge.
Chi, Jeffrey Dean, and Neoklis Polyzotis
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
AutoPilot uses decentralized reinforcement learning to continuously adjust BFT protocol parameters online, achieving 49.8% lower end-to-end latency than static defaults in dynamic environments.
An experimental evaluation of learned spatial indexes derives a decision tree for index selection under varying data skew, query selectivity, and storage conditions, validated on real point sets.
citing papers explorer
-
AutoPilot: Learning to Steer High Speed Robust BFT
AutoPilot uses decentralized reinforcement learning to continuously adjust BFT protocol parameters online, achieving 49.8% lower end-to-end latency than static defaults in dynamic environments.