Automated algorithm selection discovery via LLMs
Emmanuel Lujan, Rabab Alomairy, Rushil Shah
The DARPA-MIT SmartSolve project tackles the challenge of dynamically selecting optimal algorithms and architectures through an automated discovery framework. As part of this effort, we present advances on optimizing algorithm and data structure choices tailored to linear algebra. Contributions include automated benchmarking across diverse matrix patterns, database-driven selection via Pareto analysis, and exploring large language models for automatic heuristic generation.
Julia for High-Performance Computing
Main Room 4
