TensorX
返回文献探索

Paper · arXiv 2402.14547

OmniPred: Language Models as Universal Regressors

Xingyou Song, Oscar Li, Chansoo Lee, Bangding, Yang, Daiyi Peng, Sagi Perel, Yutian Chen

14 upvotesFebruary 22, 2024arXiv 预印本
AI 摘要

OmniPred, a framework training language models as universal end-to-end regressors, outperforms traditional regression models using textual representations of parameters and values from diverse experimental data.

OmniPredlanguage modelsend-to-end regressorsGoogle Vizierblackbox optimizationnumerical regression

Abstract

Over the broad landscape of experimental design, regression has been a powerful tool to accurately predict the outcome metrics of a system or model given a set of parameters, but has been traditionally restricted to methods which are only applicable to a specific task. In this paper, we propose OmniPred, a framework for training language models as universal end-to-end regressors over (x,y) evaluation data from diverse real world experiments. Using data sourced from Google Vizier, one of the largest blackbox optimization databases in the world, our extensive experiments demonstrate that through only textual representations of mathematical parameters and values, language models are capable of very precise numerical regression, and if given the opportunity to train over multiple tasks, can significantly outperform traditional regression models.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
OmniPred: Language Models as Universal Regressors | TensorX