# Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

Source: [Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How](<https://www.sota2.com/research/paper/68fa72431e209131cea555fe>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:22:12.513Z

Authors: Sebastian Pineda Arango, Fabio Ferreira, Arlind Kadra, Frank Hutter, Josif Grabocka

Published: 2023-06-06T16:15:26.000Z

## Abstract

With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly searches for the optimal pretrained model and the hyperparameters for finetuning it. Our method transfers knowledge about the performance of many pretrained models with multiple hyperparameter configurations on a series of datasets. To this aim, we evaluated over 20k hyperparameter configurations for finetuning 24 pretrained image classification models on 87 datasets to generate a large-scale meta-dataset. We meta-learn a multi-fidelity performance predictor on the learning curves of this meta-dataset and use it for fast hyperparameter optimization on new datasets. We empirically demonstrate that our resulting approach can quickly select an accurate pretrained model for a new dataset together with its optimal hyperparameters.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.03828>)

[PDF](<https://arxiv.org/pdf/2306.03828.pdf>)