<ul data-eligibleForWebStory="true"><li>Text-to-text regression is proposed as a scalable alternative for predicting metric outcomes of large systems where traditional tabular regression methods struggle.</li><li>A 60M parameter encoder-decoder model trained from random initialization achieves high accuracy in predicting resource efficiency on Google's massive compute cluster scheduling system.</li><li>The text-to-text regression model outperforms tabular approaches with a near-perfect rank correlation and significantly lower mean squared error across the system fleet.</li><li>The model demonstrates adaptability to new tasks with few-shot examples and effectively captures complex outcome distributions, with important implications for universal simulators of real-world outcomes.</li></ul>

Performance Prediction for Large Systems via Text-to-Text Regression

Discover more