Co-evolving LLM-generated solutions with their evaluators enables discovery of novel database algorithms that outperform state-of-the-art baselines, including a query rewrite policy with up to 6.8x lower latency.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Hermes enables constant-time global aggregations and in-place updates on homomorphically encrypted databases by embedding precomputed statistics in packed ciphertexts and using polynomial slot masking and shifting.
LLMs can outperform DTA on index recommendations for some workloads but remain less reliable with practical adoption challenges.
citing papers explorer
-
AI-Driven Research for Databases
Co-evolving LLM-generated solutions with their evaluators enables discovery of novel database algorithms that outperform state-of-the-art baselines, including a query rewrite policy with up to 6.8x lower latency.
-
Hermes: Efficient Global Homomorphic Aggregation over Mutable Packed Ciphertexts
Hermes enables constant-time global aggregations and in-place updates on homomorphically encrypted databases by embedding precomputed statistics in packed ciphertexts and using polynomial slot masking and shifting.
-
Evaluating the Practical Effectiveness of LLM-Driven Index Tuning with Microsoft Database Tuning Advisor
LLMs can outperform DTA on index recommendations for some workloads but remain less reliable with practical adoption challenges.