← all papers · overview

LLM Performance Predictors Are Good Initializers For Architecture Search

Abstract

In this work, we utilize Large Language Models (LLMs) for a novel use case: constructing Performance Predictors (PP) that estimate the performance of specific deep neural network architectures on downstream tasks. We create PP prompts for LLMs, comprising (i) role descriptions, (ii) instructions for the LLM, (iii) hyperparameter definitions, and (iv) demonstrations presenting sample architectures

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).