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.
Algo- rithms with predictions.Commun
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Learning-augmented LRU achieves 1-consistency and O(k)-robustness for GPU caching with low overhead, implemented in LCR to cut P99 TTFT by up to 28.3% on LLM workloads and raise throughput by up to 24.2% on DLRM workloads.
citing papers explorer
-
Learning Augmented Exact Exponential Algorithms
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.
-
Toward Robust and Efficient ML-Based GPU Caching for Modern Inference
Learning-augmented LRU achieves 1-consistency and O(k)-robustness for GPU caching with low overhead, implemented in LCR to cut P99 TTFT by up to 28.3% on LLM workloads and raise throughput by up to 24.2% on DLRM workloads.