Variational Model Merging for Pareto Front Estimation in Multitask Finetuning

The article introduces a new Bayesian approach called Variational Model Merging, aimed at enhancing the quality of Pareto front estimates in multitask finetuning by using flexible non-Gaussian posteriors. This method builds on existing model-merging techniques and demonstrates that utilizing more complex posterior distributions leads to superior estimates of Pareto fronts, validated through empirical results on vision and language transformers. This advancement is significant for practitioners as it provides a more efficient way to determine optimal task-mixing strategies, potentially reducing computational costs associated with Pareto front estimation.